Agents IA
opik
Open-source LLM observability: trace, evaluate and monitor apps and agents
★ 22,5 k étoilesApache-2.0
Voir le guide →// agents · traceloop/openllmetry
openllmetry
openllmetry est un projet de agents IA open source, créé par traceloop (traceloop/openllmetry sur GitHub). Il compte 7 477 étoiles sur GitHub et 1 134 forks, il est publié sous la licence Apache-2.0 et a été mis à jour pour la dernière fois sur GitHub le 6 octobre 2026.
OpenTelemetry-native observability for LLM apps.
★ 7,5 k étoiles⑂ 1,1 k forksApache-2.0mis à jour oct. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet
Détails du projet
- Étoiles GitHub
- 7 477
- Forks
- 1 134
- Licence
- Apache-2.0
- Dernière mise à jour sur GitHub
- 6 octobre 2026
- Catégorie
- Agents IA
- Type de fiche
- Guide d'installation complet
- Site officiel
- Official site
// fonctionnement
Comment ça marche
- Pick a first task
Choose one real workload to test the project against.
- Download the project
Clone it locally and read through the getting-started guide.
- Wire up dependencies
Install the stack it needs and set any environment variables.
- Run and verify
Execute the starter example and check results before going further.
// fonctionnalités
Pourquoi on l'adore
OpenTelemetry-based
Vendor-neutral traces, metrics, and logs.
LLM-aware
Captures prompts, completions, and token usage.
Python instrumentation
Drop-in tracing for Python LLM apps.
Traceloop-backed
Maintained by the Traceloop team.
Apache-2.0
Permissive licensing.
Production focus
Built for operating GenAI in production.
Advertisement
// lancez-le
Lancez-le vous-même
- Step 1 — Install
Add the instrumentation package to your project.
pip install openllmetry - Step 2 — Initialize
Initialize tracing at your app's startup per the docs.
# see docs for the init snippet - Step 3 — Point at a backend
Send traces to your OpenTelemetry collector or backend.
# works with Jaeger, Grafana, and other OTel backends
// cas d'usage
Ce que vous pouvez créer
- Trace LLM calls across a production app.
- Monitor token cost and latency per feature.
- Debug multi-step agent runs with traces.
- Feed LLM telemetry into existing observability stacks.
Advertisement
// faq
Questions fréquentes
Who maintains OpenLLMetry?
It is maintained by Traceloop at traceloop/openllmetry, with 1,134 forks.
Is OpenLLMetry free to use?
Yes. It is released under the Apache-2.0 license, which permits commercial use, modification, and redistribution. Read the LICENSE file for the exact terms.
Do I need a paid API to use it?
The instrumentation is free; you bring your own tracing backend, self-hosted or otherwise.
How does it compare to LangSmith or Langfuse?
It is OpenTelemetry-native and vendor-neutral, so it fits existing observability stacks rather than a dedicated LLM platform.
How do I get started?
Install the package, initialize it in your app per the docs, and point it at your collector.
// continuez l'exploration
Outils similaires
Agents IA
logfire
Pydantic Logfire: Python and AI observability on OpenTelemetry — SQL-queryable traces, metrics, and logs
★ 4,5 k étoilesMIT
Voir le guide →Agents IA
phoenix
Observability and evaluation for AI apps — see what your agents do.
★ 11,7 k étoilesNOASSERTION
Voir le guide →Agents IA
future-agi
One open platform to simulate, evaluate, guardrail, trace, and optimise LLM and agent apps, self-hostable.
★ 2,1 k étoilesApache-2.0
Voir le guide →Agents IA
helicone
Open-source LLM observability: monitor, evaluate, and experiment.
★ 6,2 k étoilesApache-2.0
Voir le guide →Agents IA
RagaAI-Catalyst
Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic syst…
★ 16,2 k étoilesApache-2.0
Voir le guide →// alternatives
Alternatives en Agents IA
Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si openllmetry ne vous convient pas.
- openclaw★ 391,6 k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294,9 k
An agentic skills framework & software development methodology that works.
- ECC★ 275,2 k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252,0 k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245,5 k
DeepSeek's plugin-based agent harness where everything is a plugin.
// plus en agents
Plus en Agents IA
Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de openllmetry — continuez à explorer de part et d'autre.
- guardrails★ 7,5 k
Put guardrails on LLMs: validate outputs before they reach users.
- Guardrails★ 7,3 k
Programmable guardrails to keep LLM systems safe and on rails.
- reef★ 7,5 k
Reef — infrastructure for continually self-improving agents: weight-training and harness-evolving deployments.
- Voyager★ 7,2 k
Voyager — the open-ended embodied Minecraft agent that writes its own skills and keeps learning for life.
- honcho★ 7,5 k
Honcho — Plastic Labs' memory library for stateful agents that learn about their users over time.
- swarms★ 7,2 k
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Obtenir openllmetry
Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.