Categories / AI Agents

Open Source AI Agents Apps

Discover open source AI agent frameworks, runtimes, and orchestration tools. Build autonomous agents that plan, use tools, and execute multi-step tasks.

86 apps available

Apps in AI Agents

go
Go
60%
MIT

Obot

AI Agents

1,014

An open-source MCP platform for organizations — host MCP servers, run MCP registries, monitor usage, and build agents and chatbots on top of the Model Context Protocol from one self-hosted deployment.

View details
87
Repo Health
70
Technical
70
Dependency
Built with
Go 60%
Svelte 27%
TypeScript 12%
Updated 1 weeks ago
Go
33%
Apache 2.0

CubeSandbox

AI Agents · Developer Tools · Security

12,344

Instant, concurrent, hardware-isolated MicroVM sandboxes for AI agents — E2B-API compatible, sub-60ms cold starts, and a built-in zero-trust egress proxy, all self-hostable at scale.

View details
83
Repo Health
88
Technical
63
Dependency
Built with
Go 33%
Rust 26%
C 23%
Updated 1 weeks ago
Go
45%
Apache 2.0

e2a

AI Agents · Automation

189

Give your AI agents a real, authenticated email address — with SPF/DKIM-verified inbound, HMAC-signed delivery, WebSocket fan-out, and human-in-the-loop approval built in.

View details
78
Repo Health
80
Technical
71
Dependency
Built with
Go 45%
TypeScript 27%
Python 14%
Updated 1 weeks ago
Go
99%
Apache 2.0

klaw

AI Agents · Devops

637

kubectl for AI Agents — manage, schedule, and scale your AI workforce with a single binary that deploys in seconds.

View details
39
Repo Health
74
Technical
83
Dependency
Built with
Go 99%
Updated 5 months ago
Go
86%
Apache 2.0

fabrica

AI Agents · AI Development · Devops

45

Ephemeral, VM-isolated "Agent Computers" for AI agents — a Kubernetes-native REST API backed by Kata Containers microVMs.

View details
34
Repo Health
75
Technical
81
Dependency
Built with
Go 86%
Updated 2 months ago

About AI Agents

AI Agents are autonomous software systems that go beyond chatting — they perceive context, plan multi-step workflows, call external tools, write and execute code, and loop until a goal is achieved. Unlike traditional AI assistants that respond to single prompts, agents operate over extended horizons, recovering from failures and adapting to new information.

The open-source ecosystem has exploded with agent frameworks, runtimes, memory systems, and orchestration layers — giving developers full control over how agents reason, what tools they access, and how they handle long-running tasks without being locked into a proprietary platform.

Join founders buildingwith open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on Substack
Join 750+ subscribers