AI Agents
agentops
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI …
★ 5.9k starsMIT
View guide →// agents · openlit/openlit
openlit
openlit is an open-source agents project by openlit (openlit/openlit on GitHub). It has 2,814 GitHub stars and 418 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 1 October 2026.
Open-source observability for AI agents: trace, evaluate, guard, and improve.
💎 Hidden gem★ 2.8k stars⑂ 418 forksApache-2.0updated 2026-10
▦ 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
- openlit/openlit
- GitHub stars
- 2,814
- Forks
- 418
- License
- Apache-2.0
- Last updated on GitHub
- 1 October 2026
- Category
- Agents
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Instrument your agent
Add OpenLIT tracing to your agent code.
- Collect traces
See every model call, tool use, and decision.
- Evaluate quality
Score agent behavior against your standards.
- Guard and improve
Add guardrails and iterate on weak spots.
// features
Why people love it
OTEL-based tracing
Standard observability under the hood.
Agent evaluation
Score quality, not just latency.
Guardrails
Catch bad behavior before users see it.
Harness engineering
Improve everything around the model.
ClickHouse backend
Scales to serious trace volumes.
Multi-agent support
Works with Claude Code, Codex, and more.
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/openlit/openlit.git cd openlit - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project’s launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Debug why an agent made a bad call.
- Evaluate agent quality over time.
- Add guardrails to a production agent.
- Monitor agent costs and latency.
Advertisement
// faq
Questions, answered
Who maintains OpenLIT?
It is an open-source project at openlit/openlit with 418 forks.
Is OpenLIT free for commercial use?
Yes. Apache-2.0 licensed.
How is it different from Langfuse?
It is OTEL-native and frames itself around harness engineering.
Can I self-host it?
Yes. It is designed to run on your own stack.
Which frameworks are supported?
Claude Code, Codex, and others; check the docs for integrations.
// keep exploring
Similar tools
AI Agents
mcp-use
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
★ 10.7k starsMIT
View guide →AI Agents
Langgraph
Build resilient agents
★ 42.7k starsMIT
View guide →AI Agents
opik
Open-source LLM observability: trace, evaluate and monitor apps and agents
★ 22.5k starsApache-2.0
View guide →AI Agents
phoenix
Observability and evaluation for AI apps — see what your agents do.
★ 11.7k starsNOASSERTION
View guide →AI Agents
helicone
Open-source LLM observability: monitor, evaluate, and experiment.
★ 6.2k starsApache-2.0
View guide →// alternatives
Alternatives in Agents
The most-starred other Agents projects in the LibreAI catalogue — the realistic shortlist if openlit 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 Agents
Nearby Agents projects in the catalogue, closest in stars to openlit — keep exploring the shelf either side of it.
- qwen-audio-agent★ 2.8k
Real-time voice runtime that keeps AI agents talking, working, and present.
- tons-of-skills-marketplace★ 2.8k
Model-agnostic marketplace of agent skills with a harness-free canonical layer.
- godot-ai★ 2.9k
Production-grade MCP server for Godot — let AI build scenes, edit scripts and wire your game live
- Paper2Any★ 2.8k
Turn papers, text, or topics into editable research figures and slides.
- jadx-ai-mcp★ 2.9k
JADX plugin + MCP server that lets LLMs analyze Android APKs live — decompile, review, find vulnerabilities
- PhyAgentOS-core★ 2.8k
Recursive self-improving physical agent OS — verified, evidence-based execution for robots and simulators
Get openlit
Free and open — grab the source, star the repo, and start creating.