Search

The missing transactional layer for AI agents side effects. At-most-once execution, human-in-the-loop approvals, queryable audit trail.

OpenSpawn — An open source multi-agent coordination platform

A data-driven, cryptographically signed, registry-backed AI operating system, with capability-scoped execution and graph-executable workflows — living inside your projects, running through a recursive MCP that goes as deep as you dare.

The minniest of the mini openclaw-knockoff for protocol testing and micro-sized deployments

[PAUSED] Autonomous Agent Orchestration Framework — multi-agent LLM coordination with 28 subsystems, built on Bun

Autonomous agents for everyone

UK legal API for AI agents and researchers.

The component framework for AI.

Multi-Agent Orchestration at Scale

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括359个大模型，覆盖chatgpt、gpt-5.2、o4-mini、谷歌gemini-3-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3-max、qwen3.5-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.5、ernie4.5、MiniMax-M2.5、deepseek-v3.2、Qwen3.5、llama4、智谱GLM-5、GLM-4.7、LongCat、gemma3、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。

👾 Open source implementation of the ChatGPT Code Interpreter

A curated list of Generative AI tools, works, models, and references

SRE Agent - CNCF Sandbox Project

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

Simplify interactions with Large Language Models

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

LLM QA, Observability, Evaluation and User Feedback