An open-source RAG-based tool for chatting with your documents.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Unified framework for building enterprise RAG pipelines with small, specialized models
- parsing
- retrieval-augmented-generation
- agents
- generative-ai-tools
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
- ai-vtuber
- ai-waifu
- ai
- neuro-sama
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
the LLM vulnerability scanner
- ai
- llm-evaluation
- llm-security
- security-scanners
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.
TranslatedSprix AI at 屿智同行 (Yuzhi Tongxing, "island wisdom traveling together") × 保研岛 (Baoyan Dao, "Baoyan Island") — an open-source benchmark for AI agents in Baoyan advising and application planning.
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
ChatGPT Telegram Bot running in AWS Lambda
- chatgpt
- aws-lambda
- openai
- python
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
- ai4science
- llm
- multiagent-systems
- prompt-engineering
An NLP library for Uralic languages such as Finnish, Skolt Sami, Moksha and so on. Also supporting some non-Uralic languages such as Spanish, French, Arabic, Swedish, Norwegian, Russian and English. LLMs, FSTs and More!
- nlp-library
- uralic-languages
- finnish
- sami
Friendly Environment for Neural Networks (fenn) is a simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.
- beginner-friendly
- beginner-project
- deep-learning
- deep-neural-networks
The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
- data-harmonization
- data-science
- depression
- harmonisation
MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain