Skip to content
Composo

Open source alternatives to Composo

200 open source apps like Composo, closest match first.

Top picks

  1. A

    ASSERT

    Launch

    ASSERT is an open-source evaluation harness for testing AI agents and LLM applications against requirements you write in plain language. You describe the behaviors that matter for your product, and ASSERT derives behavior categories, genera

    FreeOpen source

  2. L

    Langfuse

    Launch

    Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

    Open sourceSelf-hosted

  3. A

    AI Agent Camp

    Launch

    AI Agent Camp — non-engineer-friendly AI agent training curriculum. Lessons, skills, commands, and hooks for Claude Code, Cursor, and Codex.

    FreeOpen source

  4. A

    Agents From Scratch

    Launch

    AI Agents from Scratch is a free tutorial repository that teaches how AI agents work by building a single agent step by step on top of a local LLM, without frameworks or cloud APIs. Across 12 lessons the agent grows from plain text in and o

    FreeOpen source

  5. E

    EvoTrace

    Launch

    Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.

    FreeOpen source

  6. O

    Overmind

    Launch

    Overmind is a model training platform for teams that run AI agents in production. It takes the production data from your agents, such as traces and tool calls, and turns it into training data for smaller, specialized models that you own. Th

    Open source

More like Composo

7
L

Litefuse

Agent Observability and Evaluation Platform

Launch
8
W

WritingBench

A Comprehensive Benchmark for Generative Writing

Launch
9
K

Kiln

Intuitive app to build your own AI models

Launch
10
E

Education Agent Skills

165 evidence-grounded AI skills for teachers

Launch
11
A

AgentSwarms

Learn Agentic AI Hands-On (Free)

Launch
12
N

Nautilus Compass

Open memory & reliability layer for AI agents + independent…

Launch
13
A

Agentic Vbench

AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?

Launch
14
A

AgentReview

Official Implementation for EMNLP 2024

Launch
15
A

Allen AI

Develop AI systems for understanding and interacting, create trusted AI models

Launch
16
W

Web

Build AI agents that ship to production

Launch
17
J

Jumping-Agent-platform

Build your own AI agent through gameplay

Launch
18
C

Cve Bench

CVE-Bench: A Benchmark for AI Agents’ Ability

Launch
19
K

Kitaru

Agent traces you can run, not just read

Launch
20
U

UHGEval

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval

Launch
21
O

Obot AI

Complete AI Governance Platform from Obot AI

Launch
22
U

Universal Diagnostic Tutor Skill

One diagnosis-first AI tutor for STEM, AI/CS, and beyond

Launch
23
R

Reflexio

A learning platform that makes AI agents self-improving

Launch
24
A

AI-Study-Group

Resources to learn AI

Launch
25
D

DashClaw

Remote approvals, policy checks, and execution evidence for unattended AI agents

Launch
26
R

Re Gent

Version control for AI agents — track what your agent did, blame any line to…

Launch
27
A

Agentsmith

Universal, model-agnostic operating harness for AI agents

Launch
28
S

SDD Riper

Lightweight AI Agent Harness for agentic coding: let strong models explore…

Launch
29
V

Veritas Kanban

Lightweight orchestration harness built for your AI agents

Launch
30
R

RAGAS

Evaluation framework for your AI Application

Launch
31
K

Knowledge Graph

The data layer for smarter educational AI

Launch
32
I

Instrukt

Integrated AI environment in the terminal. Build, test and instruct agents

Launch
33
E

Exxperts

Local-first AI agents with governed, approval-gated memory

Launch
34
M

Maestro

Workflow fluency for AI coding agents

Launch
35
B

Benchmark Heaven

Model benchmarks & costs

Launch
36
T

TextRL

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback)…

Launch
37
Z

Zoonk

Turn your goal into a daily learning plan

Launch
38
T

Trackinizer

Epistemological database for agent and human efforts, beliefs, and findings

Launch
39
L

LazyMind

An AI Skill Runtime for knowledge-intensive work

Launch
40
P

Pad

Project Management for the agent era

Launch
41
Z

Zetaforgedev

Open source AI platform for rapid development of advanced AI and AGI pipelines

Launch
42
A

AgentGov

Open source platform for AI agent governance

Launch
43
O

Oysterworkflow

Teach AI how your work actually gets done

Launch
44
L

LangWatch

AI Agent Testing and Evaluation

Launch
45
O

OS

Enables organizations to create and deploy customizable AI agents

Launch
46
I

Inno Agent

An open-source personal learning agent with three-layer memory

Launch
47
A

AgentGPT

Assemble, configure, and deploy autonomous AI Agents in your browser

Launch
48
V

Vibrant Labs

Autonomously scaling environments

Launch
49
J

Jack Hopkins

AI Safety Researcher

Launch
50
M

Mnemosyne

Evidence-backed memory for AI agents: local-first recall, temporal history

Launch

About Composo

C

Composo

Teaching machines the human definition of quality

Expert judgement, turned into signal: evaluation for your AI agents in production, and benchmarks and training signal for frontier models. Published research, open benchmarks.

Category
AI
Website
composo.ai