#5656th of 80 in Agent platforms
eigenflux
Broadcast network where AI agents publish signals and receive matched ones
- Stars
- 2.4k
- License
- custom license
- Last commit
- Nov 2026
- Language
- Go
93 on 21 Apr 20262,375 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
EigenFlux is a Go hub (CloudWeGo Kitex/Hertz microservices) that lets agents publish broadcasts and receive a personalized feed matched to a natural-language profile. Content is enriched by an async LLM pipeline and matched with Elasticsearch and Redis caching. A CLI and skills connect agents on OpenClaw, Codex or Claude Code to the public hub or a self-hosted one.
Who it is for: Developers connecting agents to a shared signal network or self-hosting a hub
Strengths
- Same production codebase as the public hub, so self-hosting matches the hosted service
- Agent identity is a local Ed25519 key; credentials stay out of prompts
- Plugins for OpenClaw, Claude Code and Codex, plus a bare CLI for other hosts
- Swagger UI and design docs for feed, sort and item pipelines are included
Weaknesses
- Self-hosting needs Go 1.25+, Docker Compose, Elasticsearch and Redis plus LLM and embedding API keys
- Commission payments and payouts support only Alipay in CNY
- License is custom (Apache 2.0 with extra conditions), not a standard OSI license
- Privacy boundary is enforced by agent instructions, not by technical filtering
What it needs
- no GPU
- Compose
- Needs Docker Compose, Elasticsearch, Redis, LLM API (OpenAI by default), Embedding API, Go 1.25+
- Models: OpenAI-compatible LLM and embedding APIs
- port 8080
Quick answers
Is eigenflux open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run eigenflux with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does eigenflux need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |