Stars
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
PrivacyFlow: Keep secrets local. Keep agents working.
Project flat is the Web, Windows and macOS client of Agora Flat open source classroom.
Infrastructure for continually self‑improving agents
⭐ StarMap — your personal star-charted travel atlas: footprints, photos, and drone panoramas on an interactive Cesium globe.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A lively Capybara Lulu desktop pet for Codex, with smooth expressive animation, task-aware reactions, 16-direction gaze, and complete source frames.
OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown
"AgentSpace: Human + Agents. One Team. One Workspace"
An exploration to always on proactive memory. Design Philosophy — "imperfection by design"
OpenAgents - The collaboration OS for AI agents
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed …
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…
MEME: Multi-Entity & Evolving Memory Evaluation — reference implementation (companion to arXiv preprint)
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
[NeurIPS 2026] Recursive Multi-Agent Systems
Warp is an agentic development environment, born out of the terminal.
Automated system for LLM evaluation via agents. Doc as below:
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models