RAGChecker: A Fine-grained Framework For Diagnosing RAG
Repository Index
110,088 visible repositories in the index
1,561–1,584 of 2,423 · Most stars
NativeMind: Your fully private, open-source, on-device AI assistant
Dromedary: towards helpful, ethical and reliable LLMs.
A Roadmap to Build World Models for Robot Policy Evaluation
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
- llm
- reasoning
- rl
An Open-Source Multimodal AIGC Solution based on ComfyUI + MCP + LLM https://pixelle.ai
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.
- github-copilot
- openai-responses
- anthropic-compatible
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
- autonomous-agents
- language-model
- llm
- mathematical-reasoning
Evaluate your LLM's response with Prometheus and GPT4 💯
- evaluation
- litellm
- llm
- llmops
The only TypeScript package you will ever need
The repository host gives no description.
Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
Tools to train a generative model on arbitrary audio samples
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
- alignment
- reward
- reward-model
- rlhf
PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
AI model square and chat with AI.
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications