Skip to content

πŸ€– Awesome list of AI Agents

Fix broken table-of-contents anchor and stale repository URLs (#777)

Wu Shuwend3c899069591
diff --git a/README.md b/README.md
index ce8215b..be285b5 100644
--- a/README.md
+++ b/README.md
@@ -14,7 +14,7 @@ Awesome Agents is a curated list of open-source tools and products to build AI a
- [Research](#research)
- [Conversational / General Agents](#conversational--general-agents)
- [Game / Simulation](#game--simulation)
- - [Knowledge Management](#knowledge-management)
+ - [Memory - Knowledge Management](#memory---knowledge-management)
- [Automation](#automation)
- [Browser](#browser)
@@ -83,7 +83,7 @@ Awesome Agents is a curated list of open-source tools and products to build AI a
- [Open-RAG-Eval](https://github.com/vectara/open-rag-eval): an open source RAG evaluation framework that does not require golden answers, and can be used to evaluate performance of RAG tools connected to an AI Agent (Agentic RAG)
- [EvoAgentX](https://github.com/ANative-Lab/EvoAgentX): EvoAgentX is building a Self-Evolving Ecosystem of AI Agents, it will give you automated framework for evaluating and evolving agentic workflows. ![GitHub Repo stars](https://img.shields.io/github/stars/ANative-Lab/EvoAgentX?style=social)
- [Arize-Phoenix](https://github.com/Arize-ai/phoenix): Arize-Phoenix is an open source library for agent testing, evaluation and observability. ![GitHub Repo stars](https://img.shields.io/github/stars/Arize-ai/phoenix?style=social)
-- [Manifest](https://github.com/mnfst/manifest): Open-source, real-time cost observability platform for AI agents. Track tokens, costs, messages, and model usage with a local-first dashboard. Supports 28+ LLM models, OTLP ingestion, self-hosted. ![GitHub Repo stars](https://img.shields.io/github/stars/mnfst/manifest?style=social)
+- [Manifest](https://github.com/mnfst/llm-gateway): Open-source, real-time cost observability platform for AI agents. Track tokens, costs, messages, and model usage with a local-first dashboard. Supports 28+ LLM models, OTLP ingestion, self-hosted. ![GitHub Repo stars](https://img.shields.io/github/stars/mnfst/llm-gateway?style=social)
- [agent-qa](https://github.com/vostride/agent-qa): Self-improving agentic QA harness for web and mobile tests. Write tests in natural language, use memory to adapt to UI changes, and catch regressions before releases ship. ![GitHub Repo stars](https://img.shields.io/github/stars/vostride/agent-qa?style=social)
- [Latitude](https://github.com/latitude-dev/latitude-llm): Open-source LLM observability and evaluation platform for AI agents. Traces agent runs, clusters production failures into issues, and auto-generates evals from real-world failures. Built on OpenTelemetry, self-hostable. ![GitHub Repo stars](https://img.shields.io/github/stars/latitude-dev/latitude-llm?style=social)
- [ClawMetry](https://github.com/vivekchand/clawmetry): Open-source, zero-config real-time observability dashboard for AI agent runtimes (Claude Code, Codex, Cursor, Hermes and more) with sessions, token and cost analytics, and OTLP ingestion. ![GitHub Repo stars](https://img.shields.io/github/stars/vivekchand/clawmetry?style=social)
@@ -134,7 +134,7 @@ Awesome Agents is a curated list of open-source tools and products to build AI a
- [Orca](https://github.com/echoVic/orca-agent): A DeepSeek-native terminal coding agent in Rust with OS-level sandboxing, persistent goal mode, background tasks, and verification gates ![GitHub Repo stars](https://img.shields.io/github/stars/echoVic/orca-agent?style=social)
- [fractal](https://github.com/plasma-ai/fractal): Hierarchical agent loops with recursive self-organization. ![GitHub Repo stars](https://img.shields.io/github/stars/plasma-ai/fractal?style=social)
- [OpenCodeReview](https://github.com/alibaba/open-code-review): An open-source hybrid code reviewer combining deterministic rules with an LLM agent (tool-use, line-level comments); self-hostable, bring-your-own model. ![GitHub Repo stars](https://img.shields.io/github/stars/alibaba/open-code-review?style=social)
-- [BitFun](https://github.com/GCWing/BitFun): Open-source desktop agent with a Rust runtime for real repositories, browser, terminal, and desktop execution, extensible through MCP, Skills, and custom agents. ![GitHub Repo stars](https://img.shields.io/github/stars/GCWing/BitFun?style=social)
+- [OpenBitFun](https://github.com/GCWing/OpenBitFun): Open-source desktop agent with a Rust runtime for real repositories, browser, terminal, and desktop execution, extensible through MCP, Skills, and custom agents. ![GitHub Repo stars](https://img.shields.io/github/stars/GCWing/OpenBitFun?style=social)
- [CompozyOS](https://github.com/compozy/compozy): Open-source operating system for AI agents β€” plug in the agent CLIs you already use and run them as a team on loops and schedules, with shared memory, permissions and approvals ![GitHub Repo stars](https://img.shields.io/github/stars/compozy/compozy?style=social)
- [Ouroboros (Agent OS)](https://github.com/Q00/ouroboros): A Socratic interview gates the spec on an ambiguity score, then one command drives execution, a staged evaluation gate, and a budgeted evolution loop that runs the semantic stage only. ![GitHub Repo stars](https://img.shields.io/github/stars/Q00/ouroboros?style=social)
- [Atomic Agent](https://github.com/AtomicBot-ai/atomic-agent): Local-first CLI and TUI coding agent that runs open-weight models entirely on your machine via a llama.cpp fork. ![GitHub Repo stars](https://img.shields.io/github/stars/AtomicBot-ai/atomic-agent?style=social)