Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
Repository Index
132,218 visible repositories in the index
1,057–1,080 of 2,136 · Most stars
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
- machine-learning
- pytorch
- contrastive-learning
- neuroscience-methods
NativeMind: Your fully private, open-source, on-device AI assistant
A Roadmap to Build World Models for Robot Policy Evaluation
Dromedary: towards helpful, ethical and reliable LLMs.
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.
Universal Basic Chat
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Give your coding agent the power to write and run agent evals.
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
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
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
- ai-agents
- ci-cd
- evals
- llm-evaluation
Evaluate your LLM's response with Prometheus and GPT4 💯
- evaluation
- litellm
- llm
- llmops
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
- alignment
- reward
- reward-model
- rlhf
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.
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
Measuring and evolving with the frontier of agent work
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
Evaluation tool for LLM QA chains
LLM-based ontological extraction tools, including SPIRES