The fastest-moving corner of AI, tracked live: the research, frameworks, models, and launches driving autonomous systems forward. Auto-refreshes throughout the day.
Title-anchored arXiv search, so results are actually about agents.
Repos tagged ai-agents on GitHub, active in the last 60 days.
Latest releases from the agent frameworks most people build on.
Trending agent-oriented models on the Hugging Face Hub.
Trending agent Spaces you can run in the browser right now.
Agent projects shown on Hacker News in the past two weeks.
Top Hacker News discussions specifically about AI agents.
The latest Agentic AI writing from the community (Medium doesn't expose clap counts, so this is newest-first, not vote-ranked).
Lab blog posts whose titles mention agents.
Sep 10
Agentic AI is moving from bounded task execution toward systems that retain consequential state, continue operating and adapt across task boundaries. That shift creates a control problem that current harnesses largely s…
Sep 10
When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compounds shared errors. Existing collective decision-making methods, inclu…
Sep 10
Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often rely on costly execution-based evaluation and substantial task data.…
Sep 10
Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for optimizing agent execution. Existing harness evolution methods typical…
Sep 10
In recent years, artificial intelligence has made extraordinary progress thanks to large-scale models capable of generalization and the generation of complex outputs. However, transferring this potential into embodied a…
Sep 10
Embedding an intelligent agent in an existing application creates a persistent coordination problem: users can revise goals and manipulate shared objects while delegated execution continues. We argue that dependable int…
Sep 10
Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon exploration and rarely test whe…
Sep 10
Long-horizon robot manipulation requires memory, but not necessarily inside the action policy. To address such tasks, current agentic systems often combine VLAs with planners and geometric tools, sometimes using additio…
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor…
The agent that grows with you
DeepSeek Harness: Everything is a Plugin.
The context API to search, scrape, and interact with the web at scale. 🔥
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemin…
Agents that use the browser.
All-Hands-AI/OpenHands
langchain-ai/langchain
openai/openai-agents-python
crewAIInc/crewAI
browser-use/browser-use
microsoft/autogen
image text to text
text generation
text generation
text generation
text generation
text generation
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Ojus Chugh
Dreamfind
Zeeshan Shabbir
RK
Ilia Sokolov
David Rodenas PhD
Pankaj Kumar
Shamim Bhuiyan
Noor Mohammad
Hugging Face
Google DeepMind