#4444th of 52 in Agent platforms
intentkit
Self-hosted cluster of collaborating AI agents with a skill system and API
- Stars
- 6.5k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Jun 2026
- Language
- Python
6,423 on 4 Apr 20266,521 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
IntentKit runs a team of AI agents on your own server, where agents can call each other and use pluggable skills. It can be deployed with Docker, imported as a Python library, or driven from other applications through its built-in API. The README also lists optional Web3 and social media integrations.
Who it is for: Self-hosters building multi-agent teams reachable via API or Python
Strengths
- Multiple agents can call and interact with each other
- Usable as a Python library or through built-in API endpoints
- README states agents cannot access your secret keys
- Extensible skill system for adding capabilities
Weaknesses
- README gives no hardware, database or model provider requirements
- Does not accept pull requests; issues only
- Setup details live in external docs, not the README
- Crypto and social integrations may add scope you do not need
What it needs
- Docker + Compose
- Compose runs PostgreSQL, Redis
Quick answers
Is intentkit open source?
Yes. Its code is on GitHub under the MIT license.
Can you run intentkit with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Agent platforms
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| 3 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | open-designDesign workspace that drives your coding agent to build prototypes, decks and video | 92 out of 100 |