🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Repository Index
47,133 repositories indexed
1–21 of 21 · Most stars
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
TranslatedOpen-source AI API relay benchmark, rankings & switcher for Claude Code / Codex: measured availability, latency and price
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
- natural-language-generation
- natural-language-processing
- nlg
- nlp
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
- accuracy-decline
- ai-safety
- audit-trail
- fact-checking
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
- ai-text-detection
- explainable-ai
- interpretability
- mechanistic-interpretability
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
- agent-architecture
- git-automation
- llm-agents
- program-synthesis
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
- game-ai
- hearthstone
- reinforcement-learning
- rust
Official Repository of paper OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
- agent-evaluation
- evaluation-framework
- evaluation-metrics
- java
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
- bland
- dspy
- livekit
- llm
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
- agent-orchestration
- cli
- developer-tools
- llm-agents
The E2E AI testing tool | No ML Overhead
Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.
- ai-agents
- ai-testing
- llm
- llm-evaluation
Catch silent failures in agent workflows by verifying real system state