talkie is a vintage language model from 1930

Offical Implementation for "Recursive Multi-Agent Systems"

Anthropic's original performance take-home, now open for you to try!

Building the Virtuous Cycle for AI-driven LLM Systems

Benchmark for vector databases.

🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw (Clawdbot/Moltbot), Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Con…

Reinforcement learning environments for compiler and program optimization tasks

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

A browser-based desktop where AI Agent operates every app through natural language.

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

MemEvolve & EvolveLab

SWE-chat: Coding Agent Interactions From Real Users in the Wild

Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.

This is the official codebase for paper: Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.

AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

MemOCR: an OCR-driven visual memory agent.

Stash — persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.

OpenClaw plugin — turn Claude Code CLI into a programmable, headless coding engine with plenty of tools, agent teams, and multi-model proxy

Any model. Every tool. Zero limits.

COS-PLAY: Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Game Play

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Hugging Face's take home challenge for post-training internships, now open for you to try!

This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language

Harbor is a framework for running agent evaluations and creating and using RL environments.

AI-assisted academic posters.

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.