AI Agents
Haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and…
★ 26.6k starsApache-2.0
View guide →// agents · CodeSoul-co/Hypha
Hypha
Hypha is an open-source ai agents project by CodeSoul-co (CodeSoul-co/Hypha on GitHub). It has 447 GitHub stars and 126 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 4 September 2026.
A harness-oriented framework for production-grade agent applications.
★ 447 stars⑂ 126 forksApache-2.0updated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- CodeSoul-co/Hypha
- GitHub stars
- 447
- Forks
- 126
- License
- Apache-2.0
- Last updated on GitHub
- 4 September 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Define the job
Write down the task or workflow you want the agent to handle.
- Get the code
Clone the repository and read the README's prerequisites.
- Set up your environment
Install dependencies and configure keys or endpoints.
- Try the quickstart
Run the sample script and check the output against the docs.
// features
Why people love it
Harness-first
The agent loop is the core abstraction.
Production-grade
Caching, evals, and memory included.
Event-sourced
Agent activity as a replayable log.
Agent runtime
Built-in execution environment.
TypeScript
Modern typed stack.
Apache-2.0
Open and commercially friendly.
Advertisement
// run it
Run it yourself
- Step 1 - Clone the repo
Download the source and move into the project folder.
git clone https://github.com/CodeSoul-co/Hypha.git cd Hypha - Step 2 - Install dependencies
Pull in the Node packages the project needs.
npm install - Step 3 - Build or run it
Treat these as starting points - the README documents the exact commands.
npm run build
// use cases
What you can build
- Build a production agent with harness discipline.
- Prototype event-sourced agent logging.
- Add caching and evals to an agent app.
- Explore harness-oriented architecture.
Advertisement
// faq
Questions, answered
Who is behind Hypha?
The project lives at CodeSoul-co/Hypha and has attracted 126 forks. Browse its commit history and contributor list for a sense of maintenance pace.
Is Hypha free to use?
Yes - it is Apache-2.0 licensed, so it is free for commercial use with attribution.
Do I need a paid API to use it?
The framework itself is free - but you will need a model to drive it, which usually means your own API key or a local model.
Hypha vs Strands harness SDK?
Both are harness-centric, but Hypha is a fuller framework with memory, caching, and evals built in, while Strands' SDK is a lighter harness structure. Pick Hypha for batteries-included, Strands for flexibility.
Where should I start?
The README and the official docs site are the fastest path: run the quickstart example first, then adapt it to your use case.
// keep exploring
Similar tools
Agents
trpc-agent-go
Go framework for production agent systems: graphs, tools, memory, A2A, MCP.
★ 1.8k starsApache-2.0
View guide →AI Agents
langroid
Langroid: a principled Python framework for building LLM multi-agent applications (from CMU/UW researchers)
★ 4.1k starsMIT
View guide →AI Agents
ruoyi-ai
Enterprise-grade AI agent framework with multi-provider LLM management, secure knowledge bases and high-precision RAG, visual workflow orchestration, and mul…
★ 5.7k starsMIT
View guide →AI Agents
omnigent
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewrit…
★ 10.4k starsApache-2.0
View guide →AI Agents
swarms
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
★ 7.2k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if Hypha is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to Hypha — keep exploring the shelf either side of it.
- agent-world-model★ 465
Snowflake's Agent World Model: synthesise 1,000 executable MCP tool-use environments for agentic RL.
- MMLU-Pro★ 429
The tougher, more robust successor to the MMLU benchmark.
- invariant★ 467
Guardrails for building secure, robust agents.
- RAMPART★ 419
Safety testing for agents, right in pytest.
- vigil-llm★ 504
Detect prompt injections and jailbreaks before they hit your LLM.
- A-mem-sys★ 401
Agentic memory for LLM agents, from a published research project.
Get Hypha
Free and open — grab the source, star the repo, and start creating.