zhayujie/cowagent

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel....

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 12 minutes ago
Added to GitGenius on August 31st, 2026
Created on August 7th, 2022
Open Issues & Pull Requests: 43 (+0)
Number of forks: 10,330
Total Stargazers: 46,741 (+0)
Total Subscribers: 310 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 31.1 hours
Mean response time: 76.7 days
90th percentile: 174.1 days
Tracked items: 755

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "question" is answered fastest, typically in about 6 hours, while "enhancement" waits about 3 days. Only 8% of issues opened in the past year have been closed. Three people close 89% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 20
New in 7 days: 3
Closed in 7 days: 2
Avg open age: 62 days
Stale 30+ days: 7
Stale 90+ days: 1

Recent activity

Opened in 7 days: 3
Closed in 7 days: 2
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • needs check (375)
  • stale (272)
  • enhancement (61)
  • question (19)
  • duplicate (11)
  • bug (9)
  • documentation (6)
  • help wanted (3)

Detailed Description

CowAgent is an open-source AI agent framework that plans tasks, executes tools and skills, maintains memory and knowledge, and evolves through self-improvement across multiple language models and communication channels.

The tool addresses the need for autonomous AI assistants that can operate continuously and independently. It works by accepting high-level objectives, breaking them into actionable tasks, executing external tools and custom skills, and building persistent knowledge bases that inform future decisions. The framework supports multiple LLM providers and integrates with various messaging platforms, allowing deployment as a persistent service on personal computers or servers.

Teams should adopt this tool if they need a lightweight, extensible agent framework that can run continuously without cloud dependencies. It suits projects requiring autonomous task planning, tool integration, and long-term memory across conversations. The tool is designed for easy deployment and customization through skill plugins, making it accessible for developers who want to extend agent capabilities without deep framework modifications.

The project maintains active development with regular updates and community engagement across multiple communication channels. The codebase shows ongoing refinement of core agent functionality and expansion of integrations. Documentation and skill marketplace resources are actively maintained to support users building custom extensions.