Skip to content

The Stacks

Wing of Agents

Autonomous and semi-autonomous agent frameworks and runtimes.

Free to explore · curated by OneWave AI

157 agents projects in this wing of the Stacks. Review status is shown for every entry.

AI searches are sent to OpenAI.

Review is in progress. 1,407 projects are queued and none has been approved yet. Everything unreviewed is discovery metadata imported from GitHub — listed, not vetted.

Request a review · What we check

Ranked by total stars at the last daily refresh. This is not stars earned during the selected period. Star counts in the AI category are known to be inflated by fake-star campaigns, so activity and license are shown first.

22 projects matching “harness”
affaan-m organisation mark

ECC

affaan-m/ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Pushed 4 days ago.MIT LicenseJavaScriptAgents302.0k+4.4k
lobehub organisation mark

lobehub

lobehub/lobehub

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Pushed today.OtherTypeScriptAgents85.2k+1.1k
Mintplex-Labs organisation mark

anything-llm

Mintplex-Labs/anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Pushed today.MIT LicenseJavaScriptAgents68.2k+255
alibaba organisation mark

open-code-review

alibaba/open-code-review

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

Pushed yesterday.Apache License 2.0GoAgents50.0k+546
zhayujie organisation mark

CowAgent

zhayujie/CowAgent

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)

Pushed yesterday.MIT LicensePythonAgents47.9k+98
agentscope-ai organisation mark

QwenPaw

agentscope-ai/QwenPaw

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Pushed yesterday.Apache License 2.0PythonAgents37.7k+273
langchain-ai organisation mark

deepagents

langchain-ai/deepagents

The batteries-included agent harness.

Pushed today.MIT LicensePythonAgents31.2k
rohitg00 organisation mark

agentmemory

rohitg00/agentmemory

#1 Persistent memory for AI coding agents based on real-world benchmarks

Pushed today.Apache License 2.0TypeScriptAgents30.3k
yc-software organisation mark

qm

yc-software/qm

Multiplayer agent harness for teams

Pushed today.MIT LicenseTypeScriptAgents15.7k
mindfold-ai organisation mark

Trellis

mindfold-ai/Trellis

The best agent harness.

Pushed 2 months ago.GNU Affero General Public License v3.0TypeScriptAgents15.1k
NevaMind-AI organisation mark

memU

NevaMind-AI/memU

Personal memory across agents

Pushed 3 days ago.OtherPythonAgents14.6k+18
aden-hive organisation mark

hive

aden-hive/hive

Multi-Agent Harness for Production AI

Pushed 5 days ago.Apache License 2.0PythonAgents11.2k+15
HarnessMD organisation mark

munder-difflin

HarnessMD/munder-difflin

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

Pushed today.MIT LicenseJavaScriptAgents9.5k
mvschwarz organisation mark

openrig

mvschwarz/openrig

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

Pushed today.Apache License 2.0TypeScriptAgents8.8k
FailproofAI organisation mark

failproofai

FailproofAI/failproofai

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

Pushed today.OtherTypeScriptAgents8.8k
loopx-project organisation mark

loopx

loopx-project/loopx

Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes.

Pushed today.Apache License 2.0PythonAgents6.6k
ModelEngine-Group organisation mark

nexent

ModelEngine-Group/nexent

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

Pushed yesterday.MIT LicensePythonAgents6.2k
EverMind-AI organisation mark

Raven

EverMind-AI/Raven

The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Pushed today.Apache License 2.0PythonAgents6.2k
the-open-agent organisation mark

openagent

the-open-agent/openagent

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

Pushed 7 days ago.Apache License 2.0GoAgents5.7k
lintsinghua organisation mark

claude-code-book

lintsinghua/claude-code-book

《御舆:解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析,15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站:

Pushed 12 days ago.No license detectedPythonAgents4.4k+15
CommandCodeAI organisation mark

command-code

CommandCodeAI/command-code

Command Code AI — the best coding agent for open models.

Pushed 2 days ago.No license detectedAgents4.2k+15
davidondrej organisation mark

cloudroom

davidondrej/cloudroom

Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud.

Pushed yesterday.Apache License 2.0TypeScriptAgents1.6k
Agents — open-source AI agents — Techandria