AI Agents
Agent frameworks, autonomy, MCP, tool use, multi-agent orchestration
825 articles across 182 editions
Articles
- [Editorial] -- 2026-02-24
- [Editorial] -- 2026-02-24
- [Editorial] -- 2026-02-24
- The Missing Semester of Your CS Education – Revised for 2026 -- 2026-02-24
- [Editorial] -- 2026-02-24
- [Editorial] -- 2026-02-24
- BakeLens/crust -- 2026-02-24
- hazcod/claudleak -- 2026-02-24
- klawsh/klaw.sh -- 2026-02-24
- [Editorial] -- 2026-02-24
- [Editorial] -- 2026-02-24
- [Editorial] Bugcrowd Guide to Prompt Injection -- 2026-02-23
- [Editorial] arXiv Research -- 2026-02-23
- [Editorial] Exploitation Validator -- 2026-02-23
- What Breaks Embodied AI Security: LLM Vulnerabilities, CPS Flaws, or Something Else? -- 2026-02-23
- [Editorial] The AI Automation Ceiling -- 2026-02-23
- [Editorial] Faramesh — Research Paper -- 2026-02-23
- [Editorial] Faramesh — Core Repository -- 2026-02-23
- [Editorial] Faramesh — Video Introduction -- 2026-02-23
- Charlotte: Open Source Browser MCP Server — 136x More Token-Efficient for Agents -- 2026-02-23
- Kilntainers: Give Every Agent an Ephemeral Linux Sandbox via MCP [Open Source] -- 2026-02-23
- [Editorial] Run-Agent -- 2026-02-23
- [Editorial] Manifold -- 2026-02-23
- [Editorial] arXiv Research -- 2026-02-23
- [Editorial] Introducing AgentDB v3 -- 2026-02-23
- [Editorial] Agentic Quality Engineering -- 2026-02-23
- Zero-day CSS: CVE-2026-2441 exists in the wild -- 2026-02-21
- Microsoft says bug causes Copilot to summarize confidential emails -- 2026-02-21
- [Editorial] WebMCP — MCP for the Web -- 2026-02-21
- [Editorial] Video: AI & Security Perspectives -- 2026-02-21
- [Editorial] Why Probabilistic Engineering Breaks Deterministic Systems -- 2026-02-21
- IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST -- 2026-02-20
- Forensic audit on local AI assistant: 40.8% of tasks were fabricated -- 2026-02-20
- [Editorial] OpenAI Practical Guide to Building Agents -- 2026-02-20
- [Editorial] Generalized Hill Climbing Runtime -- 2026-02-20
- [Editorial] Build Quality Skill: How I Ship Software 10x Faster -- 2026-02-20
- AI45Lab/TrinityGuard: A Unified Framework for Safeguarding Multi-Agent System Safety -- 2026-02-20
- HackMyClaw — Adversarial Security Challenge for AI Agents -- 2026-02-20
- [Editorial] Video Feature -- 2026-02-20
- Study: Self-generated Agent Skills are useless -- 2026-02-19
- [Editorial] Claude Code RAG with Local Vector Database -- 2026-02-19
- Ibrahim-3d/conductor-orchestrator-superpowers -- 2026-02-19
- agno-agi/dash -- 2026-02-19
- ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies -- 2026-02-18
- Google Deepmind has released their take on multi-agent orchestration they're calling Intelligent AI Delegation -- 2026-02-18
- [Editorial] BeadHub — AI Creative Tool -- 2026-02-18
- I built a local AI coding agent with an 8-layer security sandbox — then had ChatGPT try to break it for 240+ rounds -- 2026-02-18
- [Editorial] How to Sandbox Claude Code with Nono -- 2026-02-18
- tomascupr/sandstorm — One API call. Full Claude agent. Completely sandboxed. -- 2026-02-18
- [Editorial] AI Agent Security Strategy -- 2026-02-18
- [Editorial] WebMCP and Enhanced Page Protocol -- 2026-02-17
- WebMPC, has anyone used it? -- 2026-02-17
- [Editorial] Voice-Controlled UI Agent Design -- 2026-02-17
- [Editorial] The Agentic Operating System -- 2026-02-17
- Forked OpenClaw to run fully air-gapped (no cloud deps) -- 2026-02-17
- Anthropic still won't give the Pentagon unrestricted access to its AI models -- 2026-02-17
- OpenAI uses internal version of ChatGPT to identify staffers who leak information: report -- 2026-02-17
- FormalTask: Open-source declarative orchestration for Claude Code agents -- 2026-02-17
- [Editorial] Get Shit Done -- 2026-02-17
- [Editorial] Karpathy Gist -- 2026-02-17
- [Editorial] AI DevOps and Developer Productivity -- 2026-02-16
- OpenClaw Skill for Cost-Optimized Model Routing Based on Task Complexity -- 2026-02-16
- [Editorial] O16G Platform -- 2026-02-16
- [Editorial] GrubCrawler — Web Crawling Tool -- 2026-02-16
- [Editorial] Storybook — UI Component Development -- 2026-02-16
- [Editorial] Video Content -- 2026-02-16
- [Editorial] ACM Research Paper -- 2026-02-16
- [Editorial] https://mrinal.com/articles/agent-identities -- 2026-02-13
- [Editorial] https://labs.zenity.io/p/perplexity-comet-a-reversing-story -- 2026-02-13
- Jasonzzt/ComfyUI-CacheDiT -- 2026-02-12
- ysharma3501/LuxTTS -- 2026-02-12
- [Editorial] https://www.linkedin.com/pulse/when-brain-os-meets-real-operating-systems-rafael-knuth-4hcsf -- 2026-02-11
- [Editorial] https://docs.entire.io/core-concepts -- 2026-02-11
- Why System Prompts are failing your local agent builds (and why you need a Logic Floor) -- 2026-02-11
- I built an MCP server that syncs Cursor, Claude Desktop, and Windsurf with one brain [Open Source] -- 2026-02-11
- [Editorial] https://forge-quality.dev/articles/orchestra-learns-to-tune-itself -- 2026-02-10
- I built an embodied agent in Minetest using Llama 3.2 + Vector Memory. Tonight, she passed the "Turing Test" by refusing to work because she was "tired. -- 2026-02-10
- PlanDrop - Chrome extension to drop prompts from browser to AI coding agents on remote servers -- 2026-02-10
- [Editorial] https://github.com/ikennaokpala/forge -- 2026-02-09
- [Editorial] https://github.com/ruvnet/claude-flow/issues/1098 -- 2026-02-09
- [Editorial] https://factory.strongdm.ai/ -- 2026-02-09
- [Editorial] https://www.linkedin.com/posts/reuvencohen_both-the-new-codex-parallel-agents-and-the-activity-7425697703445196800-xCjI -- 2026-02-09
- [Editorial] https://www.linkedin.com/posts/reuvencohen_most-intelligent-systems-fail-because-they-activity-7425306022862344192-TPtE -- 2026-02-06
- [Editorial] https://www.linkedin.com/pulse/continuous-behavioral-verification-ongoing-path-done-ikenna-okpala-k9kme -- 2026-02-06
- Need Help: AI Model for Local PDF & Image Extraction on Win11 (32GB RAM + RTX 2090) -- 2026-02-06
- kmizu/embodied-claude -- 2026-02-06
- benjiyaya/HeartMuLa_ComfyUI -- 2026-02-06
- adithya-s-k/manim_skill -- 2026-02-04
- Running DOOM and Super Mario 64 Inside a PDF File -- 2026-02-04
- Nemotron-Personas-Brazil: Co-Designed Data for Sovereign AI -- 2026-02-04
- [Editorial] https://www.linkedin.com/posts/patrickdebois_github-jedi4everaddt-run-ai-coding-agents-activity-7424653736788099072-7Aov -- 2026-02-04
- MCP + Ghidra for AI-powered binary analysis — 110 tools, cross-version function matching via normalized hashing -- 2026-02-04
- Arguably, the best AI code review MCP server (with Serena integration) -- 2026-02-04
- EPYC 8124P (Siena) Build for Agentic Coding -- 2026-02-04
- The 80% Problem in Agentic Coding – Addy Osmani -- 2026-02-04
- [Editorial] https://www.linkedin.com/posts/dragan-spiridonov_agenticqe-agenticsfoundation-qualityengineering-ugcPost-7424143676773277696-EikW -- 2026-02-03
- rodydavis/agent-skills-generator -- 2026-02-03
- An Event Badge Re-Imagined As A Cyberdeck -- 2026-02-03
- Open-Vocabulary Functional 3D Human-Scene Interaction Generation -- 2026-02-03
- [Editorial] https://unhypedai.substack.com/p/the-knowledge-we-never-had-to-explain -- 2026-02-02
- [Editorial] https://www.linkedin.com/posts/reuvencohen_i-keep-coming-back-to-this-realization-and-activity-7415150024868892672-E4rE -- 2026-02-02
- [Editorial] https://humanemulator.co/ -- 2026-01-30
- Generating skills for api+local CUAs via noVNC demonstration recording MCP -- 2026-01-30
- Our Agent Rebuilt Itself in 26 Hours. AMA👀 -- 2026-01-30
- I built a multi-agent orchestration layer for Claude Code - sharing in case it's useful to anyone -- 2026-01-30
- I got tired of my AI agents overwriting each other's code, so I built a conflict manager for them -- 2026-01-27
- Skill.md: An open standard for agent skills -- 2026-01-27
- Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective -- 2026-01-27
- [Editorial] https://github.com/ruvnet/ruvector/blob/claude/clawdbot-ruvector-setup-RHW3a/npm/packages/ruvbot/docs/FEATURE_COMPARISON.md -- 2026-01-27
- Can companies "hack" ChatGPT to promote them? -- 2026-01-27
- [Editorial] Vercel Labs' agent-browser + claude flow -- 2026-01-26
- I wrote a URI scheme for agent identity that doesn't break when you move things -- 2026-01-26
- [Open Sourse] I built a tool that forces 5 AIs to debate and cross-check facts before answering you -- 2026-01-26
- An underrated way to turn AI code into real AI agents -- 2026-01-26
- [Editorial] https://github.com/Combat-Drones-Detection-AI/Icarus -- 2026-01-26
- [Editorial] https://unhypedai.substack.com/p/the-ai-operating-model-moment -- 2026-01-26
- devstral small 2 vs glm 4.7 flash for agentic coding -- 2026-01-23
- HeartMuLa/HeartMuLa-oss-3B -- 2026-01-23
- [Editorial] agentic qe -- 2026-01-22
- Demo: On-device browser agent (Qwen) running locally in Chrome -- 2026-01-22
- Am I the only one in to enjoy the latest remote code sessions on Claude.ai with my full agentic config? Anyone else had some breakthrough with it? -- 2026-01-22
- [Editorial] https://www.linkedin.com/posts/reuvencohen_llms-are-a-dead-end-not-because-they-are-activity-7419916372274470912-_5Lc -- 2026-01-22
- All major AI stupid again, alternatives? -- 2026-01-22
- [Resource] AI Guardrails: Open-source middleware to add PII Redaction & Injection Defense to local LLMs -- 2026-01-21
- Jailbreak Challenge: Can You Break My Agent??? -- 2026-01-21
- Do AI agents need TLS-style identities and ‘certificates’? -- 2026-01-21
- Demo: On-device browser agent (Qwen) running locally in Chrome -- 2026-01-20
- Agent observability is way different from regular app monitoring - maintainer's pov -- 2026-01-20
- charIesding/agent-dashboard -- 2026-01-20
- Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems -- 2026-01-20
- [Editorial] https://www.linkedin.com/posts/cole-medin-727752184_ive-been-testing-vercels-agent-browser-activity-7418832504754872320-PCA0 -- 2026-01-19
- [Editorial] https://addyosmani.com/blog/good-spec -- 2026-01-19
- AgentStudio: A VLA-based Kiosk Automation Agent using Gemini 3 and LangGraph -- 2026-01-19
- Claude Skills Magic -- 2026-01-19
- 7x Longer Context Reinforcement Learning in Unsloth -- 2026-01-19
- openbmb/AgentCPM-Explore -- 2026-01-19
- black-forest-labs/FLUX.2-klein-4B -- 2026-01-19
- [Editorial] https://www.linkedin.com/posts/reuvencohen_announcing-claude-flow-v3-a-full-rebuild-activity-7417928335160262656-NYqJ -- 2026-01-16
- [Editorial] https://www.linkedin.com/posts/sandstream_i-just-shipped-ralph-inferno-10-to-npm-activity-7417606358654406657-zBPY -- 2026-01-16
- [Editorial] https://www.linkedin.com/posts/rasmuswiding_parallel-ai-agents-the-complete-infrastructure-activity-7417646422436777984-D1Zw -- 2026-01-16
- Ralph Loop inspired me to build this - AI decides what Claude Code does next orchestrating claude code until task is done -- 2026-01-16
- [Editorial] https://www.linkedin.com/posts/calebsima_due-to-popular-demand-here-is-my-%F0%9D%97%96%F0%9D%97%BC%F0%9D%97%B1%F0%9D%97%B6-activity-7417371887598514176-J6eg -- 2026-01-15
- [Editorial] https://www.linkedin.com/posts/cole-medin-727752184_ralph-wiggum-is-everywhere-in-ai-right-now-activity-7417369954963910656-PQ3c -- 2026-01-15
- [Editorial] https://www.linkedin.com/posts/craigmcluckie_coding-agents-are-crippling-oss-communities-activity-7417250625391915009-pcbA -- 2026-01-15
- Agent reliability testing is harder than we thought it would be -- 2026-01-15
- The Ralph Loop Made Easy -- 2026-01-15
- [Editorial] https://github.com/pnocera/skilld -- 2026-01-15
- [Editorial] https://www.linkedin.com/posts/hiltch_today-we-are-launching-openwork-an-open-source-ugcPost-7417259004294488064-KvyW -- 2026-01-15
- [Editorial] https://www.linkedin.com/posts/claudio-stamile_if-youre-building-agents-youve-probably-activity-7416401402438205440-t9V_ -- 2026-01-13
- [Editorial] https://www.linkedin.com/posts/matthewrwadams_threatmodeling-agenticai-aiagents-ugcPost-7416389760795176960-Ytut -- 2026-01-13
- The hidden memory problem in coding agents -- 2026-01-13
- I gave Claude Code a single instruction file and let it autonomously solve Advent of Code 2025. It succeeded on 20/22 challenges without me writing a single line of code. -- 2026-01-13
- CloudAI-X/claude-workflow -- 2026-01-13
- [Editorial] https://www.linkedin.com/posts/reuvencohen_a-year-ago-deepseek-landed-and-everyone-argued-activity-7416833905653329921-Xt9R -- 2026-01-13
- Qwen3 235 VL hallucinates Tool calls -- 2026-01-13
- [Editorial] https://www.sciencedirect.com/science/article/abs/pii/S1084804511000774 -- 2026-01-13
- AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing -- 2026-01-13
- [Editorial] https://github.com/leochlon/pythea/tree/main/strawberry -- 2026-01-12
- [Editorial] https://arxiv.org/abs/2509.11208 -- 2026-01-12
- One cargo install gives your AI 142 tools to perceive and control your machine - rmcp-presence -- 2026-01-09
- AI agents for searching and reasoning over internal documents -- 2026-01-09
- I built Plano - a framework-friendly data plane with orchestration for agents -- 2026-01-09
- I built a TUI to manage multiple Claude Code agents in devcontainers (works great on mobile too) -- 2026-01-09
- System: Control your Mac from anywhere using natural language -- 2026-01-09
- Connect any LLM to all your knowledge sources and chat with it -- 2026-01-08
- Have claude code interact with another claude code session interactively to test a plugin im building -- 2026-01-08
- Semantic geometry for visual grounding -- 2026-01-08
- zai-org/AutoGLM-Phone-9B -- 2026-01-08
- facebook/sam-audio-large -- 2026-01-08
- [Editorial] https://www.linkedin.com/posts/andriyburkov_a-major-breakthrough-in-reinforcement-learning-activity-7414543177648472064-_omq -- 2026-01-08
- AskUserQuestionTool: if I have another kid, I know what I am going to name them. -- 2026-01-07
- [Editorial] https://www.linkedin.com/posts/reuvencohen_ralph-wiggum-as-people-are-talking-about-activity-7414663704081981440-54bK -- 2026-01-07
- [Editorial] https://joshclemm.com/writing/ralph-wiggum-future-of-coding -- 2026-01-07
- [Editorial] https://ghuntley.com/ralph -- 2026-01-07
- [Editorial] https://github.com/coleam00/Linear-Coding-Agent-Harness -- 2026-01-05
- MCP Chat Studio v2: Workspace mode, workflows, contracts, mocks, and more -- 2026-01-05
- Way to build powerful agents using natural language and code -- 2026-01-05
- GLM-4.7 running full agentic workflows in Claude Code for 15 min straight - no failures -- 2026-01-05
- I (almost) built an open-source, self-hosted runtime for AI agents in TypeScript... -- 2026-01-02
- How to get started with automated workflows? -- 2026-01-02
- Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse -- 2026-01-02
- I built HMLR, an open source (full MIT) memory layer for your agent -- 2025-12-31
- I built a "Recursive Swarm" engine inside a VS Code fork. It forces the LLM to explore 10,000 logic branches (System 2) before committing to code—trading 20 minutes of compute for accuracy. -- 2025-12-31
- BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization -- 2025-12-31
- Built an MCP Server for Andrej Karpathy's LLM Council -- 2025-12-31
- Bounded autonomy: how the "is it an agent?" question changed my QA bot design -- 2025-12-31
- eliasjudin/oai-skills -- 2025-12-31
- zai-org/GLM-ASR -- 2025-12-31
- AI Video Generation Made Easier with Wan 2.6 -- 2025-12-31
- HKUDS/MCPNext -- 2025-12-29
- virtual pet / life simulation using Ollama and Unity 6 -- 2025-12-23
- YatharthS/MiraTTS -- 2025-12-23
- stepfun-ai/Step-Audio-R1 -- 2025-12-23
- [Editorial] https://x.ai/news/grok-voice-agent-api -- 2025-12-19
- [Editorial] https://www.linkedin.com/posts/reuvencohen_sitting-on-a-beach-in-playa-del-carmen-activity-7407460969188163584-HQup -- 2025-12-19
- [Editorial] https://www.linkedin.com/posts/yotam-perkal_comparing-ai-agents-to-cybersecurity-professionals-activity-7407076565357887488-KI5M -- 2025-12-18
- Building an event-driven alternative to LangGraph because single-threaded loops are killing me. Roast my architecture. -- 2025-12-18
- Intent vectors for AI search + knowledge graphs for AI analytics -- 2025-12-17
- Cracking a 25-Year-Old Password with Claude Code -- 2025-12-17
- Weird Email Appliance Becomes AI Terminal -- 2025-12-17
- Zero-Shot Vehicle Model Recognition via Text-Based Retrieval-Augmented Generation -- 2025-12-17
- stepfun-ai/Step-Audio-EditX -- 2025-12-17
- AIDC-AI/Ovis-Image-7B -- 2025-12-17
- [Editorial] https://www.linkedin.com/posts/resilientcyber_levels-of-autonomy-for-ai-agents-activity-7406679623167803392-OFJK -- 2025-12-16
- ManiAgent: An Agentic Framework for General Robotic Manipulation -- 2025-12-16
- CUGA on Hugging Face: Democratizing Configurable AI Agents -- 2025-12-16
- AI Agent from scratch: Django + Ollama + Pydantic AI - A Step-by-Step Guide -- 2025-12-12
- [Editorial] https://github.com/humanlayer/humanlayer -- 2025-12-12
- Large update: 12 new frontier models added to the Step Game social reasoning benchmark. -- 2025-12-11
- DeepMath: A lightweight math reasoning Agent with SmolAgents -- 2025-12-11
- Nanbeige4-3B: Lightweight with strong reasoning capabilities -- 2025-12-10
- mistralai/Devstral-2-123B-Instruct-2512 -- 2025-12-10
- Can codex create multiple outputs, I check which is best? -- 2025-12-10
- stepfun-ai/GELab-Zero-4B-preview -- 2025-12-10
- Need opinion/help on my Memory System for LLM -- 2025-12-09
- FlowCoder: Visual agentic workflow customization for Claude Code and Codex -- 2025-12-09
- I built a CLI tool to manage AI configs across repos (aipaca) 🦙 -- 2025-12-09
- Counterfactual-based Agent Influence Ranker for Agentic AI Workflows -- 2025-12-08
- Run Any Model Provider on OpenWebUI immediately by discovering AI services on your LAN -- 2025-12-08
- We gave 5 LLMs $100K to trade stocks for 8 months -- 2025-12-08
- DevCrew agent swarm for accelerating your software development -- 2025-12-08
- Connect and use Nova 2 Lite with Claude Code -- 2025-12-08
- The security risks of "Emoji Smuggling" and Hidden Prompts for Local Agents -- 2025-12-08
- We were tired of guessing which local model to use for which query. built a speculative execution lib that figures it out (github) -- 2025-12-05
- Claude vs Codex: Claude won again 🏅 -- 2025-12-04
- NornicDB - API compatible with neo4j - MIT - GPU accelerated vector embeddings -- 2025-12-04
- gregorydickson/memory-graph -- 2025-12-04
- Building Deep Research: How we Achieved State of the Art -- 2025-12-03
- Claude launched 3 'explore agents' by itself -- 2025-12-02
- OpenAI realtime API opensource alternative -- 2025-12-02
- Built a Modular Agentic RAG System – Zero Boilerplate, Full Customization -- 2025-12-02
- [Editorial] https://www.linkedin.com/posts/ownyourai_i-just-finished-testing-the-new-metas-omnilingual-activity-7400801588635836416-gpo- -- 2025-12-01
- Xthebuilder/JRVS -- 2025-12-01
- tigillo/githubmodels-go -- 2025-12-01
- A Bird Watching Assistant -- 2025-12-01
- InteractComp: Evaluating Search Agents With Ambiguous Queries -- 2025-11-28
- Agent framework chaos? > Better Agents CLI -- 2025-11-28
- Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry -- 2025-11-26
- Sibyl: an open source orchestration layer for LLM workflows -- 2025-11-25
- Looking for 10 early testers building with agents, need brutally honest feedback👋 -- 2025-11-25
- Claud Agent Dashboard -- 2025-11-25
- [Editorial] https://github.com/punkpeye/awesome-mcp-servers -- 2025-11-24
- Cornserve: Microservices Architecture for Serving Any-to-Any Models like Qwen Omni! -- 2025-11-24
- How I’m Building Declarative, Shareable AI Agents With Docker cagent -- 2025-11-24
- An open-source "Slack" for AI Agents to orchestrate n8n, Flowise, and OpenAI agents in one place -- 2025-11-24
- modelscope/AgentEvolver -- 2025-11-24
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_ibm-the-2025-chief-data-officer-study-activity-7397614050433462272-0GmF -- 2025-11-21
- Do you sandbox MCPs / Claude Code / Opencode on Linux? How ? -- 2025-11-21
- Verifying hardware quality of rented gpus -- 2025-11-21
- Ollama signin docker compose -- 2025-11-21
- What's your Claude Code workflow setup? -- 2025-11-21
- Measuring political bias in Claude -- 2025-11-21
- Looking for feedback - I built Socratic, an open source knowledge base builder where YOU stay in control -- 2025-11-21
- [Editorial] https://www.linkedin.com/posts/quanta-magazine_the-awful-consequence-of-an-observer-free-activity-7396969815078236160-Vo5G?u -- 2025-11-20
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_harmful-traits-of-ai-companions-activity-7397309575928131584-8H4J -- 2025-11-20
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_realist-and-pluralist-conceptions-of-intelligence-activity-7397231918871703554-FmSP?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAAEV6YBBmyIQkYRxMIFJ7EWVq99NXg4qV4 -- 2025-11-20
- How are you all orchestrating multi-agent workflows (beyond one-shot prompt chaining)? -- 2025-11-20
- deliveryhero/asya -- 2025-11-20
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_aws-a-more-realistic-evaluation-activity-7396951453182967808-_H_c -- 2025-11-19
- Should Spec-Driven-Development have a procedural orchestrator, or an LLM? -- 2025-11-19
- Where are the gaps in Claude's "reasoning" capabilities? -- 2025-11-19
- Smart Bandage Leverages AI Model For Healing Purposes -- 2025-11-19
- miromind-ai/MiroThinker-v1.0-72B -- 2025-11-19
- GPT-5-pro is likely a universal agentic gateway / Large Agentic Model -- 2025-11-19
- BSD MAC LLM UI: Minimal, Auditable LLM Front End for Secure Environments -- 2025-11-18
- easy-oidc/easy-oidc -- 2025-11-18
- Disrupting the first reported AI-orchestrated cyber espionage campaign -- 2025-11-18
- The Challenge of Large File Checksums -- 2025-11-18
- Building A Smart Speaker Outside The Corporate Cloud -- 2025-11-18
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_i-saved-forty-ai-research-papers-recently-activity-7395547917983580160-BuOX -- 2025-11-17
- [Editorial] https://www.linkedin.com/posts/reuvencohen_i-just-finished-rebuilding-dspyts-on-top-activity-7395872853092495360-OFb8 -- 2025-11-17
- [Editorial] https://www.marktechpost.com/2025/11/08/how-to-build-an-agentic-voice-ai-assistant-that-understands-reasons-plans-and-responds-through-autonomous-multi-step-intelligence/ -- 2025-11-17
- Local-First LLM That Safely Runs Real System Tasks — Looking for Engineering Feedback -- 2025-11-17
- [MCP] Open-sourced a CSV-to-PostgreSQL loader server (vibe-coded with Claude) -- 2025-11-17
- MCP Server for Industrial IoT - Built for PolyMCP Agent Orchestration -- 2025-11-17
- Mimir - Parallel Agent task orchestration - Drag and drop UI (preview) -- 2025-11-17
- Claude helped me make a multi agent ecosystem where models interact with each other autonomously -- 2025-11-17
- AnythingLLM MCP Bridge & Prompt Injector -- 2025-11-14
- Katakate/k7 -- 2025-11-14
- Dicklesworthstone/mcp_agent_mail -- 2025-11-14
- [Editorial] https://www.linkedin.com/posts/ivandj_as-ai-agents-multiply-across-tools-and-protocols-activity-7394057385872556032-SlAQ -- 2025-11-13
- [Editorial] https://www.linkedin.com/posts/henrikgothberg_anthropic-building-effective-ai-agents-ugcPost-7394348623796350977-tcq1 -- 2025-11-13
- [Editorial] https://www.linkedin.com/posts/reuvencohen_the-latest-mcp-spec-feels-like-the-moment-activity-7394373616471072768-okAg -- 2025-11-13
- How to link an AI to a code execution environment? -- 2025-11-13
- [Editorial] https://www.linkedin.com/posts/emollick_we-need-more-papers-like-this-one-which-examines-ugcPost-7392918095805222912-YjvU?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAAEV6YBBmyIQkYRxMIFJ7EWVq99NXg4qV4 -- 2025-11-12
- Agent failures in production pushed me to simulation-based testing -- 2025-11-12
- Building agents that work like a band, not a factory line - anyone experimenting with emergent multi-agent coordination? -- 2025-11-12
- Qwen3-VL works really good with Zoom-in Tool -- 2025-11-12
- [Update] mlx-knife 2.0 stable — MLX model manager for Apple Silicon -- 2025-11-12
- Vascura BAT - configuration Tool for Llama.Cpp Server via simple BAT files. -- 2025-11-12
- Beelzebub MCP: Securing AI Agents with Honeypot Functions, Prompt Injection Detection -- 2025-11-11
- Problem Uploading PDFs in Self hosted AI -- 2025-11-11
- openai/gpt-oss-safeguard-20b -- 2025-11-11
- Dexmal/dexbotic -- 2025-11-11
- Blender 5.1 -- 2025-11-11
- Qwen/Qwen3-VL-2B-Instruct -- 2025-11-11
- [Editorial] https://www.linkedin.com/posts/stuart-winter-tear_my-company-is-forcing-me-to-become-ai-agent-activity-7393927479004135424-hI8p -- 2025-11-11
- Hephaestus: AI workflows that discover and create their own tasks as they work -- 2025-11-11
- Built my own IDE -- 2025-11-11
- Roo Code 3.30.3 Release Updates | kimi‑k2‑thinking support | UI improvements | Bug fixes -- 2025-11-11
- Claude-Bumper-Lanes - Vibe Code with Review Discipline -- 2025-11-11
- We just released a multi-agent framework. Please break it. -- 2025-11-10
- ⚡️ I scaled Coding-Agent RL to 32x H100s. Achieving 160% improvement on Stanford's TerminalBench. All open source! -- 2025-11-10
- Agent Learning via Early Experience -- 2025-11-10
- [Editorial] https://www.linkedin.com/posts/reuvencohen_claude-code-web-is-amazing-its-my-primary-activity-7393649498251644928-rAc8 -- 2025-11-10
- CodeWiki: Research-Grade Repository Documentation at Scale [Open Source] -- 2025-11-10
- Website builder powered by Claude AI - generating full websites in minutes -- 2025-11-10
- “AI, Make Me A Degree Certificate” -- 2025-11-10
- Self-hosted platform for running third-party AI agents with Ollama support (Apache-2.0) -- 2025-11-07
- Open Source Alternative to NotebookLM/Perplexity -- 2025-11-07
- Decade-qiu/Multi-Source-Media-MCP-Server -- 2025-11-07
- v0.2.0 - GenFilesMCP -- 2025-11-07
- ⚡️ Scaling Coding-Agent RL to 32x H100s. Achieving 160% improvement on Stanford's TerminalBench -- 2025-11-06
- Bifrost: A High-Performance Gateway for LLM-Powered AI Agents (50x Faster than LiteLLM) -- 2025-11-06
- Stop fighting with AI to build your project -- 2025-11-06
- OpenSkills - a open sourced and completely private Claude Skills -- 2025-11-05
- I used Llama + Droidrun to create a self-running Twitter bot -- 2025-11-05
- Thread vs. Session based short-term memory -- 2025-11-05
- kayba-ai/agentic-context-engine -- 2025-11-05
- [Editorial] Collaboration gap -- 2025-11-05
- Looking for advanced workflow tips: How are power-users integrating Claude (and other LLMs) into high-volume legal practice? -- 2025-11-05
- Lessons from interviews on deploying AI Agents in production -- 2025-11-05
- [Open Source] We deployed numerous agents in production and ended up building our own GenAI framework -- 2025-11-04
- First LangFlow Flow Official Release - Elephant v1.0 -- 2025-11-04
- zeusftk/FTK_CANVAS_AGENT_for_Comfyui -- 2025-11-04
- Qwen3-VL-32B Q8 speeds in llama.cpp vs vLLM FP8 on a RTX PRO 6000 -- 2025-11-03
- thu-coai/Glyph -- 2025-11-03
- AndroidControl-Curated: Revealing the True Potential of GUI Agents through Benchmark Purification -- 2025-11-03
- [Editorial] Agentic Flow -- 2025-11-03
- I'm making an AI similar to a vtuber using ollama, here's what I have so far! (looking for advice on anything, really) -- 2025-11-03
- Remember that simple online PDF bank converter tool making $40k/month? I did the exact same workflow with my general AI agent (only 1 prompt needed!) -- 2025-11-03
- [Editorial] Agent limits -- 2025-11-02
- [Editorial] Agent Identity -- 2025-11-02
- [Editorial] AI Defense -- 2025-11-02
- I built a privacy focused AI assistant for WearOS that supports locally hosted LLMs -- 2025-11-02
- VellumForge2 - A high performance, very configurable and really easy to use DPO dataset generation tool, create high quality datasets for completely free -- 2025-11-01
- PokeeAI/pokee_research_7b -- 2025-11-01
- [Editorial] https://itrevolution.com/articles/from-line-cookto-head-chef-orchestrating-ai-teams/ -- 2025-11-01
- [Editorial] Cursor 2.0 -- 2025-11-01
- Open Source Lovable with Custom Agents, Full Stack Support, and Local Models -- 2025-11-01
- A highly adaptable toolkit to build APIs and agents, with friendly interfaces for streaming and multimodality -- 2025-11-01
- Is it possible to enable mcp server on for specific sub agent? -- 2025-11-01
- [Editorial] AGI Defined. -- 2025-11-01
- [Editorial] Know Your Agent (KYA) -- 2025-10-30
- Spent the last few weeks falling down the Claude Agent SDK rabbit hole... built AgCluster.dev (open source) -- 2025-10-30
- Found a faster way to build Claude Skills -- 2025-10-30
- Agentic AI for Financial Crime Compliance -- 2025-10-30
- GraphScout: Intelligent Routing for Local LLM Agent Workflows -- 2025-10-30
- Show HN: Butter – A Behavior Cache for LLMs -- 2025-10-30
- katanemo/Arch-Router-1.5B -- 2025-10-30
- QAgent: A modular Search Agent with Interactive Query Understanding -- 2025-10-30
- [Open Source] We deployed numerous agents in production and ended up building our own GenAI framework -- 2025-10-29
- Claude Skills but running locally in Apple container -- 2025-10-29
- OpenSkills CLI - Use Claude Code Skills with ANY coding agent -- 2025-10-29
- Prompts avoiding Yes Men moments? -- 2025-10-29
- severity1/claude-code-prompt-improver -- 2025-10-29
- Built Coyote — An AI Agent That Feels Like Texting a Friend and released first model supporting native Async Tools -- 2025-10-29
- Distil NPC: Family of SLMs responsing as NPCs -- 2025-10-29
- nvidia/audio-flamingo-3-hf -- 2025-10-29
- microsoft/UserLM-8b -- 2025-10-29
- Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations -- 2025-10-29
- [Editorial] New calculus of coding -- 2025-10-28
- we had 2 weeks to build 5 microservices with 3 devs, tried running multiple AI agents in parallel -- 2025-10-28
- Claude Code 2.0.27 -- 2025-10-28
- steveyegge/vc -- 2025-10-28
- [Editorial] MCP Scanner, security -- 2025-10-28
- [Editorial] Data provenance -- 2025-10-28
- Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis -- 2025-10-28
- [Editorial] Virtual false positive, physical problems -- 2025-10-28
- Show HN: A fast, privacy-first image converter that runs in browser -- 2025-10-28
- Microsoft Releases AI Call Center Stack with Voice, SMS, and Memory -- 2025-10-28
- Robot Phone Home…Or Else -- 2025-10-28
- vngrs-ai/Kumru-2B -- 2025-10-27
- Training Gemma 3n for Transcription and Translation -- 2025-10-27
- Agentic Exploration of Physics Models -- 2025-10-27
- [Editorial] For the vibes -- 2025-10-27
- Best way to implement a detailed plan in an MD file? -- 2025-10-27
- sci-m-wang/ACE-open -- 2025-10-27
- StepWiser: Stepwise Generative Judges for Wiser Reasoning -- 2025-10-27
- DeepAnalyze: Agentic Large Language Models for Autonomous Data Science -- 2025-10-26
- Claude for Computer Use using Sonnet 4.5 -- 2025-10-26
- Any way to have sub-agent's keep context between invocations? -- 2025-10-26
- Learning to Steer: Input-dependent Steering for Multimodal LLMs -- 2025-10-26
- [Editorial] Promethean Fire -- 2025-10-26
- Google AI falsely named an innocent journalist as a notorious child murderer -- 2025-10-26
- Built my own MCP server for my app and was pleasantly shocked by how good it is -- 2025-10-25
- facebook/cwm -- 2025-10-25
- When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity -- 2025-10-25
- Building the Open Agent Ecosystem Together: Introducing OpenEnv -- 2025-10-25
- [Editorial] Leading AI Agent Swarms: The Agentic QE 1.2.0 Journey -- 2025-10-24
- lupantech/AgentFlow -- 2025-10-24
- jaguarliuu/xunlong -- 2025-10-24
- [Editorial] Browsers you can socially engineer -- 2025-10-24
- [Editorial] share terminal sessions using Claude Code for web -- 2025-10-24
- [Project] VT Code — Rust coding agent now with Ollama (gpt-oss) support for local + cloud models -- 2025-10-24
- How path-based pattern matching helps AI code follow your team's coding best practice -- 2025-10-24
- Show HN: FlowLens – MCP server for debugging with Claude Code -- 2025-10-24
- We built ContextAgent — a context-centric take on multi-agent systems (rethinking what an “agent” is) -- 2025-10-23
- Claude Haiku 4.5 for Computer Use -- 2025-10-23
- Sonnet 4.5 subagent Haiku question -- 2025-10-23
- disler/big-3-super-agent -- 2025-10-23
- usieye/flowma -- 2025-10-23
- [Editorial] https://github.com/jingyaogong/minimind/blob/master/README_en.md -- 2025-10-23
- After treating RL training like an SRE project, I see why they chose CISPO -- 2025-10-23
- Chatgpt or Claude for web coding assitant -- 2025-10-22
- Does Claude Desktop support MCP Server Notifications? -- 2025-10-22
- Ollama Cloud API Tool usage -- 2025-10-22
- [Editorial] https://www.linkedin.com/posts/mavlevin_aisecurity-zeroday-cybersecurity-activity-7386478715813330944-P9OP -- 2025-10-22
- Linux Capabilities Revisited -- 2025-10-22
- I got fed up with Open WebUI/LibreChat for local LLMs so I made an open source tool to turn my GPU server into an always-on assistant -- 2025-10-21
- This is how I track usage and improve my AI assistant without exposing sensitive data -- 2025-10-21
- Roadmap for building scalable AI agents! -- 2025-10-21
- My TypeScript MCP server template `mcp-ts-template` just hit v2.3.7. Declarative tool definitions. Pluggable Storage. Edge-native (Cloudflare Workers). Optional OpenTelemetry. OAuth with Scope Enforcement, etc. -- 2025-10-21
- virattt/dexter -- 2025-10-21
- UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding -- 2025-10-21
- [Editorial] https://www.linkedin.com/posts/gadievron_another-day-another-attack-on-ai-coding-activity-7386382494117466112-tXuF -- 2025-10-21
- [Editorial] https://www.linkedin.com/posts/reuvencohen_ive-seen-the-future-of-coding-and-it-activity-7386187612597714944-jXQn -- 2025-10-21
- Qwen3-vl:235b-cloud Ollama model error -- 2025-10-21
- Expose MCP at the LLM server level? -- 2025-10-20
- I got tired of copy-pasting NotebookLM answers into Claude, so I built an MCP server for it -- 2025-10-20
- Use n8n in Open WebUI without maintaining pipe functions -- 2025-10-20
- Slack sync into OpenWebUI Knowledge -- 2025-10-20
- [Editorial] Chart a path -- 2025-10-18
- [Editorial] Agentic Flow -- 2025-10-18
- [Editorial] Turbo Flow -- 2025-10-18
- Claudiomiro: How to Achieve 100% Autonomous (Complex) Coding -- 2025-10-18
- Flowchart vs handoff: two paradigms for building AI agents -- 2025-10-18
- Compare Claude Code and Codex from one prompt -- 2025-10-18
- Claude Agent SDK + Cloudflare Containers is the perfect agent platform -- 2025-10-18
- [Editorial] Getting more out of Claude Code SDK -- 2025-10-17
- [Editorial] Agentic Flow - AI Agent Framework That Gets Smarter AND Faster Every Time It Runs -- 2025-10-17
- oracle/agent-spec -- 2025-10-17
- Holy Marketplaces, Batman! -- 2025-10-16
- Show HN: Metorial (YC F25) – Vercel for MCP -- 2025-10-16
- Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search -- 2025-10-15
- How to handle long running tools in realtime conversations. -- 2025-10-15
- Anyone else having reasoning parser issue with Qwen-cli + GLM4.6 combo in vllm? -- 2025-10-15
- Plan mode coming to Codex CLI -- 2025-10-15
- Something is wrong with Sonnet 4.5 -- 2025-10-15
- Xrvitd/MeshMosaic -- 2025-10-15
- Qwen/Qwen3-VL-235B-A22B-Instruct -- 2025-10-15
- Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent -- 2025-10-15
- Vibe Coding and the Popularization of CLI Interfaces: Why Don’t Big Companies Use Millions of Users as Contributors to Improve Models? -- 2025-10-14
- rexleimo/agno-Go -- 2025-10-14
- The Silent Scientist: When Software Research Fails to Reach Its Audience -- 2025-10-14
- OpenAI’s AgentKit makes building AI agents way easier, design, chat, test, and connect everything in one place! -- 2025-10-14
- NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents -- 2025-10-14
- A list of models released or updated this week on this sub, in case you missed any (10 Oct). -- 2025-10-14
- Alibaba-NLP/Tongyi-DeepResearch-30B-A3B -- 2025-10-14
- ibm-granite/granite-4.0-micro -- 2025-10-14
- BasedBase/GLM-4.5-Air-GLM-4.6-Distill -- 2025-10-14
- A 5-minute, no-BS way to pick a local model for your real task -- 2025-10-14
- [Update] CodeLens.AI - Crowdsourced AI Leaderboard 3 Days Later: Blind Voting and What We Learned -- 2025-10-14
- How to re-create OpenAI Assistants locally? -- 2025-10-14
- M2 Max 96GB - llama.cpp with codex and gpt-oss 120b to edit files and github upload -- 2025-10-14
- Why You Should Build AI Agents with Ollama First -- 2025-10-14
- OpenWebUI en Docker no detecta modelo LLaMA3 instalado con Ollama en Linux -- 2025-10-14
- [Editorial] The Reality of Agentic Development -- 2025-10-13
- [AutoBE] achieved 100% compilation success of backend generation with "qwen3-next-80b-a3b-instruct" -- 2025-10-13
- What ACTUALLY works after testing every AI coding tool for 6 months -- 2025-10-13
- Issue with long parameter values when using tool calling with Anthropic API -- 2025-10-13
- Moondream3 and Salesforce GTA-1 for UI grounding in computer-use agents -- 2025-10-12
- vdpiya/batchi -- 2025-10-12
- Agentic generative AI for media content discovery at the national football league -- 2025-10-12
- demo: my open-source local LLM platform for developers -- 2025-10-10
- Modelfile. Do I need these tags PER prompt? -- 2025-10-10
- Script to install a bunch of AI or Dev tools automatically.. what can I add to it or improve? -- 2025-10-10
- Claude Code compaction fails with “Conversation too long” even when context is below 75% -- 2025-10-10
- Show HN: FleetCode – Open-source UI for running multiple coding agents -- 2025-10-10
- Local Terminal Access -- 2025-10-10
- xcLee001/SonicVale -- 2025-10-10
- InternRobotics/VLAC -- 2025-10-10
- meituan-longcat/LongCat-Flash-Thinking -- 2025-10-10
- LiquidAI/LFM2-1.2B-Tool -- 2025-10-10
- Hcompany/Holo1.5-7B -- 2025-10-09
- [Editorial] Agentics Newsletter -- 2025-10-09
- [Editorial] Latest batch from rUv. -- 2025-10-09
- TheAgentArk/Toucan -- 2025-10-09
- [Editorial] Increased edit speed, reduced LLM cost -- 2025-10-08
- AI agents face off -- 2025-10-08
- How to make Claude Code work for you at night? -- 2025-10-08
- tfriedel/claude-office-skills -- 2025-10-08
- What happens if AI agents start trusting everything they read? (I ran a test.) -- 2025-10-06
- High-performance mice can be used as a microphone to spy on users -- 2025-10-06
- How can I test bad behavior in model APIs without getting banned? -- 2025-10-06
- Framework or custom for local rag/agentic systems -- 2025-10-05
- Test your MCP server against Llama, no key required -- 2025-10-05
- aiprodcoder/MIXAPI -- 2025-10-05
- williavs/AGENTDL -- 2025-10-05
- Ally finally got RAG – everything runs local now -- 2025-10-05
- RawdodReverend/TermNet -- 2025-10-05
- [Editorial] https://www.linkedin.com/posts/albertochierici_lol-i-cant-stop-thinking-about-this-we-activity-7379840898626502656-bUYZ -- 2025-10-03
- Vyzer9/Valkan -- 2025-10-03
- Bypassing TLS Certificate Validation with Ld_preload -- 2025-10-03
- I built Solveig, it turns any LLM into an agentic assistant in your terminal that can safely use your computer -- 2025-10-02
- # 🥔 Meet Tater Totterson — The Local AI Assistant That Doesn’t Need MCP Servers -- 2025-10-02
- Do I need to run /init on a repo if I already have AGENTS.md? -- 2025-10-02
- sshllm/sshai -- 2025-10-02
- [Editorial] System prompts are getting outdated! -- 2025-10-02
- [Editorial] https://github.com/emcie-co/parlant -- 2025-10-02
- Microsoft Agent Framework (Preview): Making AI Agents Simple for Every Developer -- 2025-10-02
- Codex is mind blowing -- 2025-09-29
- LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs -- 2025-09-29
- Apple called out every major AI company for fake reasoning and Anthropic's response proves their point -- 2025-09-29
- Help with running Ai models with internet connectivity -- 2025-09-28
- AWS announces EC2 instance attestation -- 2025-09-28
- The Perplexity Search API -- 2025-09-28
- Reinforcement Learning with Rubric Anchors -- 2025-09-28
- PHM-Bench: A Domain-Specific Benchmarking Framework for Systematic Evaluation of Large Models in Prognostics and Health Management -- 2025-09-28
- Roo Code 3.28.6 Release Notes - GPT-5-Codex IS HERE!! -- 2025-09-28
- Main thing I use claude for is to prevent Codex from gaslighting me -- 2025-09-28
- Model answers include raw <br> tags when generating tables – how to fix in Open WebUI? -- 2025-09-28
- How to embed images in responses? -- 2025-09-28
- New Agent benchmark from Meta Super Intelligence Lab and Hugging Face -- 2025-09-27
- evalops/dspy-micro-agent -- 2025-09-27
- nvidia/NVIDIA-Nemotron-Nano-9B-v2 -- 2025-09-27
- inclusionAI/Ling-flash-2.0 -- 2025-09-27
- 1K+ schemas of agentic projects visualized -- 2025-09-26
- what AI agent framework is actually production viable and/or least problematic? -- 2025-09-26
- Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model -- 2025-09-26
- CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation -- 2025-09-26
- Link a git repo to llama.cpp server? -- 2025-09-24
- oxbshw/LLM-Agents-Ecosystem-Handbook -- 2025-09-24
- Native MCP (streamable HTTP) may be on the way -- 2025-09-24
- nvidia/NVIDIA-Nemotron-Nano-12B-v2 -- 2025-09-23
- Gaia2 and ARE: Empowering the community to study agents -- 2025-09-23
- Gaia2 and ARE: Empowering the community to study agents -- 2025-09-23
- Open sourced my AI video generation project -- 2025-09-23
- Zen, many Code CLI instances (/commands) for peaceful parallel task execution. -- 2025-09-23
- twiggy-tools/Twiggy -- 2025-09-23
- KubeAgentic-Community/KubeAgentic -- 2025-09-23
- MyLocalAI - Enhanced Local AI Chat Interface (vibe coded first project!) -- 2025-09-23
- Tesslate/WEBGEN-4B-Preview -- 2025-09-23
- tencent/SRPO -- 2025-09-23
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning -- 2025-09-22
- Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward -- 2025-09-22
- [Editorial] A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks -- 2025-09-21
- Claude Code native subagents vs. Claude Flow vs. BMAD -- 2025-09-21
- Hallucination in LLM-Based Code Generation: An Automotive Case Study -- 2025-09-21
- Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes -- 2025-09-20
- GGUF security concerns -- 2025-09-20
- Democratizing AI Safety with RiskRubric.ai -- 2025-09-20
- VoxCPM 0.5B : Tokenizer-Free TTS and Voice Cloning -- 2025-09-18
- Alibaba-NLP/Tongyi-DeepResearch-30B-A3B · Hugging Face -- 2025-09-18
- NexaAI/OmniNeural-4B -- 2025-09-18
- MobileLLM-R1-950M meets Apple Silicon -- 2025-09-18
- VS Code Chat: Introducing auto model selection (preview) -- 2025-09-18
- ircfspace/masque-plus -- 2025-09-18
- First AI Agent for DevOps/SRE and Platform Engineering -- 2025-09-17
- This AI assistant became our go-to Unity co-pilot (not just another LLM) -- 2025-09-17
- Runtime intelligence in games -- 2025-09-17
- [Editorial] Villager -- 2025-09-16
- Update: we got our revenge and now beat Deepmind, Microsoft, Zhipu AI and Alibaba -- 2025-09-16
- Building Ai Agent from Scratch (Python) -- 2025-09-15
- Siddhant-K-code/tokenvm -- 2025-09-15
- Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems -- 2025-09-15
- Qwen3-Next-80B-A3B - a big step up may be the best open source reasoning model so far -- 2025-09-14
- Qwen/Qwen3-Next-80B-A3B-Thinking -- 2025-09-14
- Nothing concrete to show yet, I just wanted to celebrate getting a remote MCP server\connector with oAuth working :) -- 2025-09-09
- The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover -- 2025-09-09
- An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees -- 2025-09-09
- [Editorial] Why Language Models Hallucinate -- 2025-09-09
- [Editorial] Compression Failures in LLMs -- 2025-09-09
- [Editorial] Active Inference AI -- 2025-09-09
- I built a Graph RAG pipeline (VeritasGraph) that runs entirely locally with Ollama (Llama 3.1) and has full source attribution. -- 2025-09-09
- Environments Hub walkthrough: Your Language Model needs better (open) environments to learn -- 2025-09-08
- The Landscape of Agentic Reinforcement Learning for LLMs -- 2025-09-08
- What are your struggles with tool-calling and local models? -- 2025-09-08
- [Project Update] From Brittle Scripts to a Resilient, Self-Auditing Architecture: The Evolution of MeganX 3.0 -- 2025-09-07
- I accidentally beat Claude Code this weekend - multi-agent-coder now #12 on Stanford's TerminalBench 😅 -- 2025-09-07
- Open-source tool to let Claude Code control your computer -- 2025-09-07
- Trustworthy Agents for Electronic Health Records through Confidence Estimation -- 2025-09-07
- Context Reasoning Benchmarks: GPT-5, Claude, Gemini, Grok on Real Tasks -- 2025-09-05
- The CLAUDE.md Framework: A Guide to Structured AI-Assisted Work (prompts included) -- 2025-09-05
- Team-intN18-SoybeanSeclab/Typhon -- 2025-09-05
- DatarusAI/Datarus-R1-14B-preview -- 2025-09-05
- Are there any SDKs that offer native tool calling functionality that can be used with any LLMs -- 2025-09-04
- Open source wrapper around AugmentCode -- 2025-09-04
- Producer Pal: control Ableton Live and make music with Claude -- 2025-09-04
- ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience -- 2025-09-04
- Jupyter Agent Dataset -- 2025-09-04
- Training & Querying 3 Ollama Models with Zer00logy: Symbolic Cognition Framework and Void-Math OS -- 2025-09-04
- unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF -- 2025-09-03
- HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds -- 2025-09-03
- Achieving 80% task completion: Training LLMs to actually USE tools -- 2025-09-03
- githubnext/gh-aw -- 2025-09-03
- Toad: Universal TUI for Agentinc Coding from Will McGugan (Rich/Textual) -- 2025-09-03
- How do you do RL 100% locally without a NVIDIA GPU? -- 2025-08-31
- NiceWebRL: a Python library for human subject experiments with reinforcement learning environments -- 2025-08-31
- Coquette Mobile - Android App, Ollama with Agentic Properties - desktop control. -- 2025-08-30
- Testers for Seed-OSS tool calling wanted! -- 2025-08-29
- Codebase to Knowledge Graph generator -- 2025-08-29
- GaohaoZhou-ops/Tello-LLM-ROS -- 2025-08-29
- Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks -- 2025-08-29
- Built an AI Agent Orchestration Platform - Handles 70% of Our Dev Tasks -- 2025-08-29
- Hobbyist project : enabling smaller language models to interact with large code bases -- 2025-08-28
- Evaluate any computer-use agent with HUD + OSWorld-Verified -- 2025-08-28
- The outer loop vs. the inner loop of agents. A simple mental model to evolve the agent stack quickly and push to production faster. -- 2025-08-28
- AgentCheck: Local AI-powered code review agents for Claude Code -- 2025-08-28
- [Editorial] The Complete Guide to BuildingAI Agents -- 2025-08-27
- Tencent/Youtu-agent -- 2025-08-27
- AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications -- 2025-08-27
- CNCF Webinar–AI Model Packaging with KitOps -- 2025-08-27
- [Editorial] Sense of Self and Time in Borderline Personality -- 2025-08-27
- [Editorial] AI and security tools. -- 2025-08-27
- MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines -- 2025-08-26
- Models to complement GPT-5? -- 2025-08-26
- Why claude.md fails and How CORE Fixes Memory in Claude Code -- 2025-08-26
- Free Preview of Qoder: The Future of Agentic Coding? -- 2025-08-25
- What MCP Servers are You Using -- 2025-08-25
- I built real-time course correction for Claude Code... and it's also a Tamagotchi -- 2025-08-25
- Not a model, but Open Source Memory framework claims to beat Mem0 on public benchmarks -- 2025-08-24
- ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents -- 2025-08-24
- CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning -- 2025-08-24
- Jules is already making excuses like a senior dev trying to explain why they pushed to main on a Friday. -- 2025-08-23
- Build a Local AI Agent with MCP Tools Using GPT-OSS, LangChain & Streamlit -- 2025-08-23
- Codanna Adds TypeScript Parsing and Modular Language Registry. Context-First Coding. -- 2025-08-23
- Presenton now supports presentation generation via MCP -- 2025-08-23
- In 44 lines of code, we have an actually useful agent that runs entirely locally, powered by Qwen3 30B A3B Instruct -- 2025-08-20
- Web Agent Memory Protocol (WAMP): Building a Shared Memory Layer for the Web -- 2025-08-20
- Learning from building my first saas using claude code -- 2025-08-20
- Generate Images with Claude and Hugging Face -- 2025-08-20
- [Editorial] AI agents are rendering GitHub's human-centric collaboration tools obsolete -- 2025-08-18
- dongguanting/ARPO -- 2025-08-18
- MCP for Research: How to Connect AI to Research Tools -- 2025-08-18
- Tencent-Hunyuan/HunyuanWorld-1.0 -- 2025-08-16
- Rediscovering Microsoft’s Oddball Music Generator From The 1990s -- 2025-08-16
- Trying to decide between Kilocode, Cline and Roo code -- 2025-08-15
- GPT-5 vs Claude Opus 4.1: Which New AI Model Wins? -- 2025-08-15
- bosonai/higgs-audio-v2-generation-3B-base -- 2025-08-14
- Chain-GPT/Solidity-LLM -- 2025-08-14
- Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need -- 2025-08-14
- 🇵🇭 FilBench - Can LLMs Understand and Generate Filipino? -- 2025-08-14
- Miro ODR: Another Deep Research Agent model just went open source -- 2025-08-14
- Is the Aider polyglot coding leaderboard still being updated? GPT-5? -- 2025-08-14
- Claude going crazy on extended thinking? -- 2025-08-14
- Building a self-hosted AI support agent (using GPT-OSS) that can both guide users and perform real actions – looking for feedback -- 2025-08-12
- Local model recommendations for lightweight, repeated screenshot analysis on macOS? -- 2025-08-12
- A free goldmine of tutorials for the components you need to create production-level agents Extensive open source resource with tutorials for creating robust AI agents -- 2025-08-12
- declare-lab/jamify -- 2025-08-12
- Intelligent-Internet/II-Search-4B -- 2025-08-12
- THUDM/GLM-4.1V-9B-Thinking -- 2025-08-12
- QwenLM/Qwen-Image -- 2025-08-12
- A specific asynchronous workflow pattern -- 2025-08-11
- mozilla-ai/any-llm -- 2025-08-11
- SunzeY/SEAgent -- 2025-08-11
- [Editorial] Three Things I Learned About Voice Agents from Kwindla Kramer -- 2025-08-09
- NVIDIA AI-Q Achieves Top Score for Open, Portable AI Deep Research (LLM with Search Category) -- 2025-08-09
- Vibe Coding an AI article generator using Onuro 🔥 -- 2025-08-09
- Claude Code v1.0.71 - Background Commands -- 2025-08-09
- Doriandarko/make-it-heavy -- 2025-08-09
- universal-tool-calling-protocol/go-utcp -- 2025-08-09
- [Editorial] Open source GUI for Claude Code -- 2025-08-08
- DoubleAgents: Fine-tuning LLMs for Covert Malicious Tool Calls -- 2025-08-08
- Hey folks, I’m one of the contributors to Bifrost, and we just launched it on Product Hunt -- 2025-08-08
- Funny but annoying time bug -- 2025-08-08
- A free goldmine of tutorials for the components you need to create production-level agents Extensive open source resource with tutorials for creating robust AI agents -- 2025-08-08
- OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use -- 2025-08-08
- So multi agents.. and context.. how does that work -- 2025-08-07
- Can you import chats in JSON? How? -- 2025-08-07
- MAESTRO, a deep research assistant/RAG pipeline that runs on your local LLMs -- 2025-08-07
- Quantize your own GGUFs the same way as your fav Unsloth Dynamic GGUFs -- 2025-08-07
- Read your code -- 2025-08-07
- weixin-omni/omni-bot-sdk-oss -- 2025-08-06
- Kart – Distributed version-control for geospatial and tabular data -- 2025-08-06
- [Editorial] Turn-Taking model for Voice AI Agents -- 2025-08-06
- [Editorial] a more mature phase of the AI cycle. -- 2025-08-05
- disler/claude-code-hooks-multi-agent-observability -- 2025-08-05
- The Parallel Lives of an AI Engineer -- 2025-08-05
- Any toolkits or predefined subagents for claude code that you think are a game changer? -- 2025-08-04
- ramakay/claude-self-reflect -- 2025-08-04
- [Editorial] Agentic Web: Weaving the Next Web with AI Agents -- 2025-08-03
- [Editorial] Gemini Flow -- 2025-08-03
- Pwn2Own Contestants hold on to Ollama exploits due to its rapid update cycle -- 2025-08-02
- Claude Code sub agents not working as expected -- 2025-08-02
- syou6162/cchook -- 2025-08-02
- I need a tutorial for coding with any model (but currently trying with DeepSeek coder) -- 2025-08-02
- The tradeoff between human and AI context -- 2025-08-02
- Building a custom LLM trained on luciform prompts + ShadeOS daemon dialogues – seeking help -- 2025-08-01
- I built a zsh plugin that turns natural language into shell commands using locally hosted Ollama -- 2025-08-01
- Some thoughts on vibe / ai-driven coding -- 2025-08-01
- [Editorial] AI in hostile environments... -- 2025-08-01
- leesh3288/CVE-2025-32023 -- 2025-08-01
- In search of riches, hackers plant 4G-enabled Raspberry Pi in bank network -- 2025-08-01
- [Editorial] PRP, google cli fork -- 2025-07-31
- [Editorial] Alternative to claude code cli -- 2025-07-31
- Why I Forked Qwen Code -- 2025-07-31
- Unwanted and unrelated changes to my code: my biggest gripe with ChatGPT -- 2025-07-31
- How to Stop Claude from Being a Yes-Man? (Anchoring Bias Problem) -- 2025-07-31
- We just open sourced NeuralAgent: The AI Agent That Lives On Your Desktop and Uses It Like You Do! -- 2025-07-30
- Help with UnifyAI – Setting Up Local LLMs and UI Integration -- 2025-07-30
- Show HN: Terminal-Bench-RL: Training Long-Horizon Terminal Agents with RL -- 2025-07-30
- Show HN: Flyde 1.0 – Like n8n, but in your codebase -- 2025-07-30
- Reachy The Robot Gets a Mini (Kit) Version -- 2025-07-30
- Hey AI, Generate Me a Hardware Code! Agentic AI-based Hardware Design & Verification -- 2025-07-30
- 100 lines of Python is all you need: A radically minimal coding agent that scores 65% on SWE-bench (near SotA!) [Princeton/Stanford NLP group] -- 2025-07-30
- [Editorial] laude Code Videos and Demos by Ruv (claude-swarm fame) -- 2025-07-29
- [Editorial] It was fun while it lasted... bring on the $1000/mo max plan. -- 2025-07-29
- Claude Code Best Practices/Tips/Tricks -- 2025-07-29
- Everything I've Learned so far About OpenAI's Agents -- 2025-07-29
- Why isn't this already a standard in robotics? -- 2025-07-28
- The 14 Pains of Billing for AI Agents -- 2025-07-28
- [Editorial] Product Requirement Prompts (PRP) -- 2025-07-28
- Red flag phrases -- 2025-07-28
- Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨ -- 2025-07-28
- [Editorial] Local voice AI, 235B LLM -- 2025-07-28
- I stopped typing. Now I just use a hotkey. I built Agent-CLI to make it possible. -- 2025-07-28
- Local cross-platform speech-to-speech and real-time captioning with OpenAI Whisper, Vulkan GPU acceleration and more -- 2025-07-28
- Devstral & Magistral as adapters of Mistral -- 2025-07-28
- [Editorial] Intersection of Product Management and Development -- 2025-07-27
- 🔓 I built Hearth-UI — A fully-featured desktop app for chatting with local LLMs (Ollama-ready, attachments, themes, markdown, and more) -- 2025-07-27
- UIGEN-X 8B supports React Headless, Flutter, React Native, Static Site Generators, Tauri, Vue, Gradio/Python, Tailwind, and prompt-based design. GGUF/GPTQ/MLX Available -- 2025-07-27
- Realtime codebase indexing for coding agents with ~ 50 lines of Python (open source) -- 2025-07-27
- Freigeist - The new Vibe Coding Platform -- 2025-07-27
- What are some unique uses of OpenWebUI that you can't get otherwise? -- 2025-07-27
- Claude Code finally told me the truth about agents :) -- 2025-07-26
- Airfare Discrimination as a Service: Airlines' Favorite New Pricing Trick -- 2025-07-25
- would this make an ai dev's life easier? -- 2025-07-25
- Let’s sync on CLI agents! What’s actually working for you? -- 2025-07-25
- Security Issue - Recent Claude Code behavior favoring fast/easy/simple took an API key and hardcoded it as a default value -- 2025-07-25
- What is the best agent framework for Qwen3? -- 2025-07-24
- Qwen/Qwen3-Coder-480B-A35B-Instruct -- 2025-07-24
- Tool calling or not, I will use anyway -- 2025-07-24
- Do you give your LLM terminal and code execution access? -- 2025-07-24
- Built Ollamaton - Universal MCP Client for Ollama (CLI/API/GUI) -- 2025-07-23
- What models/ai-code editors don't train on my codebase? -- 2025-07-23
- Can someone PLEASE ELI5 MCPs, Connectors, and Extensions for me? -- 2025-07-23
- Made My Own Auto Tool System and Enhanced Web Search Tool + Questions -- 2025-07-23
- omar-haris/cursor-buddy-mcp -- 2025-07-22
- EU is being left behinde and it sucks! -- 2025-07-22
- We built Explainable AI with pinpointed citations & reasoning — works across PDFs, Excel, CSV, Docs & more -- 2025-07-20
- Ready to go multi agent workflow on github? -- 2025-07-20
- How do we secure AI agents that act on their own? -- 2025-07-19
- Migrating a semantically-anchored assistant from OpenAI to local environment (Domina): any successful examples of memory-aware agent migration? -- 2025-07-19
- Trying to get my Ollama model to run faster, is my solution a good one? -- 2025-07-19
- GitHub - boneylizard/Eloquent: A local front-end for open-weight LLMs with memory, RAG, TTS/STT, Elo ratings, and dynamic research tools. Built with React and FastAPI. -- 2025-07-18
- A free goldmine of tutorials for the components you need to create production-level agents Extensive open source resource with tutorials for creating robust AI agents -- 2025-07-18
- Five Big Improvements to Gradio MCP Servers -- 2025-07-18
- Migrating a semantically-anchored assistant from OpenAI to local environment (Domina): any successful examples of memory-aware agent migration? -- 2025-07-18
- ARGO - A Local-First, Offline AI Agent That Puts You in Control -- 2025-07-17
- Why LangGraph overcomplicates AI agents (and my Go alternative) -- 2025-07-17
- new MCP alt. just dropped -- 2025-07-17
- pydantic/fasta2a -- 2025-07-17
- Share your MCP servers and experiments! -- 2025-07-17
- OPENCODE - Like Claude Code or Gemini CLI, but works with local models and/or paid ones as well -- 2025-07-15
- I built a Deep Researcher agent and exposed it as an MCP server! -- 2025-07-15
- awwaiid/gremllm -- 2025-07-15
- Ollama calling tools -- 2025-07-15
- 🪝 Claude-Flow@Alpha v2: We've implemented the new Claude Code Hooks in the latest Claude Flow alpha release combining hive style swarms, neural pattern recognition, and 87 MCP tools (install using: npx claude-flow@alpha) -- 2025-07-14
- k2-fsa/ZipVoice -- 2025-07-13
- K-intelligence/Midm-2.0-Base-Instruct -- 2025-07-13
- AutoTester.dev: First AI-Driven Automatic Test Tool for Web Apps -- 2025-07-13
- eiondb/eion -- 2025-07-13
- mistralai/Devstral-Small-2507 -- 2025-07-13
- What product or extension is great at autocomplete and predictive typescript/javascript and kotlin code. Cursor is out because I'm not going to pay even $1 on a greedy and scammy product, and Windsurf performs moderately well -- 2025-07-11
- trufflesecurity/force-push-scanner -- 2025-07-11
- LEGO/kube-tf-reconciler -- 2025-07-11
- agentica-org/DeepSWE-Preview -- 2025-07-11
- Thanks to you, I built an open-source website that can watch your screen and trigger actions. It runs 100% locally and was inspired by all of you! -- 2025-07-11
- Preceptor – A Local AI Focus App That Nudges You Back on Track | Waitlist + Suggestions needed -- 2025-07-11
- AGI is not multimodal -- 2025-07-09
- How Do Vision-Language Models Process Conflicting Information Across Modalities? -- 2025-07-09
- Building a Potato-based GLaDOS as an Introduction to AI -- 2025-07-07
- We built runtime API discovery for LLM agents using a simple agents.json -- 2025-07-06
- OWUI 0.6.15 OpenTelemetry (Experimental) -- 2025-07-06
- [Open Source] Moondream MCP - Vision for AI Agents -- 2025-07-05
- Kyutai's STT with semantic VAD now opensource -- 2025-07-05
- brizzai/auto-mcp -- 2025-07-05
- Lifailon/openrouter-bot -- 2025-07-05
- Augment Code?? -- 2025-07-04
- Simple-Efficient/RL-Factory -- 2025-07-04
- Ratler/airuler -- 2025-07-04
- [Setup discussion] AMD RX 7900 XTX workstation for local LLMs — Linux or Windows as host OS? -- 2025-07-04
- 🧠💬 Introducing AI Dialogue Duo – A Two-AI Conversational Roleplay System (Open Source) -- 2025-07-04
- Qwen 2.5 32B or Similar Models -- 2025-07-04
- Extending Minds with Generative AI -- 2025-07-04
- Trying to Make Llama Extract Smarter with a Schema-Building AI Agent -- 2025-07-02
- Want help in retrieving links from DB -- 2025-07-02
- Ingesting docs for context -- 2025-07-02
- Agents via OpenWebUI Functions -- 2025-07-02
- pfnet/plamo-2-translate -- 2025-06-30
- Self-Adapting Language Models -- 2025-06-27
- tencent/Hunyuan-A13B-Instruct -- 2025-06-27
- maya-research/Veena -- 2025-06-27
- jennyzzt/dgm -- 2025-06-26
- Looking to build a local AI assistant - Where do I start? -- 2025-06-24
- Real-time conversational AI running 100% locally in-browser on WebGPU -- 2025-06-24
- UI + RAG solution for 5000 documents possible? -- 2025-06-24
- Good stable voice cloning and TTS with NOT much complicated installation? -- 2025-06-24
- 🚀 I built a lightweight web UI for Ollama – great for local LLMs! -- 2025-06-24
- How to train a VLM with a dataset that has text and images? -- 2025-06-24
- Top open-source AI Agent in both SWE-bench Verified and Lite -- 2025-06-24
- AllTracker: Efficient Dense Point Tracking at High Resolution -- 2025-06-24
- I Read All of Cloudflare's Claude-Generated Commits -- 2025-06-24
- Show HN: I created an tool that creates interactive product demos in 2 minutes -- 2025-06-24
- I’m the Maintainer (and Team) behind Open WebUI – AMA 2025 Q2 -- 2025-06-24
- Eleven v3 -- 2025-06-22
- SAGA Update: Now with Autonomous Knowledge Graph Healing & A More Robust Core! -- 2025-06-21
- A free goldmine of tutorials for the components you need to create production-level agents -- 2025-06-21
- Build a full on-device rag app using qwen3 embedding and qwen3 llm -- 2025-06-21
- Build LLM from Scratch | Mega Playlist of 43 videos -- 2025-06-21
- Running an LLM on a PS Vita -- 2025-06-21
- haiku.rag a local sqlite RAG library -- 2025-06-21
- LLMs Fine-Tuning -- 2025-06-21
- Do you still use GPT APIs for demo apps? I'm leaning towards open models. -- 2025-06-21
- Guidelines on how to be a scientific sleuth released -- 2025-06-21
- Which models are you able to use with MCP servers? -- 2025-06-21
- Rig upgraded to 8x3090 -- 2025-06-21
- moonshotai/Kimi-Dev-72B -- 2025-06-21
- Show HN: DaedalOS – Desktop Environment in the Browser -- 2025-06-19
- tencent/SongGeneration -- 2025-06-19
- haasonsaas/ocode -- 2025-06-19
- dagger/container-use -- 2025-06-13
- lerobot/smolvla_base -- 2025-06-10
- brendanhogan/picoDeepResearch -- 2025-06-08
- sarvamai/sarvam-m -- 2025-06-07
- Qwen/Qwen3-Reranker-0.6B -- 2025-06-07
- Hcompany/Holo1-7B -- 2025-06-06
- huggingface/smolagents -- 2025-06-05
- openpubkey/opkssh -- 2025-06-05
- hashicorp/terraform -- 2025-06-05
- NousResearch/atropos -- 2025-06-04
- google/A2A -- 2025-06-03
- hydropix/TranslateBookWithLLM -- 2025-05-31
- sisig-ai/doctor -- 2025-05-31