🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
- Langage
- TypeScript
- Licence
- Other
- Étoiles
- 35k
- Dernière release
- v4.53.0
- Dernier push
- 2026-10-06
Trace, evaluate and monitor LLM applications.
Changements dans cette catégorie (RSS)
| Outil | Étoiles | Licence | Conditions | Auto-hébergeable | Langage | Dernière release | Dernier push |
|---|---|---|---|---|---|---|---|
| Langfuse | 35k | Other | Open core | Oui | TypeScript | v4.53.0 | 2026-10-06 |
| Opik | 22k | Apache-2.0 | Open source | Oui | Python | 2.2.92 | 2026-10-06 |
| Arize Phoenix | 12k | Other | Source disponible | Oui | Python | arize-phoenix-v20.19.0 | 2026-10-06 |
| Evidently | 8k | Apache-2.0 | Open source | Oui | Jupyter Notebook | v0.7.23 | 2026-09-29 |
| Helicone | 6.2k | Apache-2.0 | Open source | Oui | TypeScript | v2025.08.21-1 | 2026-09-16 |
| LangWatch | 4.9k | Apache-2.0 | Open source | Oui | TypeScript | langwatch-3.20.1 | 2026-10-06 |
| Agenta | 4.8k | Other | Open core | Oui | TypeScript | v0.122.1 | 2026-10-06 |
| Laminar | 3.3k | Apache-2.0 | Open source | Oui | TypeScript | v0.2.5 | 2026-10-06 |
| OpenLIT | 2.8k | Apache-2.0 | Open source | Oui | TypeScript | openlit-2.1.0 | 2026-10-05 |
9 outils
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
AI Observability & Evaluation
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
Agenta is a workspace where you and your team build agents and automations.
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.