The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
- agents
- continual-learning
- llm-agents
- self-evolving
132,241 visible repositories in the index
97–120 of 172 · Most stars
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
A test runner for agentskills.io-style AI agent skills
Compare compatible open-source local LLM projects by their metrics to assess popularity and activeness.
AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark.
OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery and remediation product, helping defenders proactively find and patch verified security flaws while minimizing both false positives and negatives. Stage 1 detects. Stage 2 attacks. What survives is real.
This custom Home Assistant integration automatically scans your entities, detects new devices, and uses AI (via cloud and local APIs) to suggest tailored automations. It supports multiple AI providers, including OpenAI, Anthropic, Google, Groq, Ollama and more! The integration provides automation suggestions via HASS notifications
Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents — knowledge that persists and compounds, for you and your AI agents. All from the CLI.
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
Command Code API 反代代理,兼容 OpenAI 与 Anthropic 接口 | Reverse proxy exposing Command Code API as OpenAI- and Anthropic-compatible endpoints
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.
Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.
PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.
Unofficial Linux packages for Claude Desktop AI assistant with automated updates.
Practical LangChain patterns and implementations for real-world LLM applications. 极客时间:LangChain实战课 - 这是LangChain框架早期设计的一系列重点模块的直接而清晰的示例和讲解。随着LangChain的快速演进,有些代码需要安装新的版本进行迭代。希望大家在快速浏览课程概念(仍有价值)的同时,自行学习LangChain最新的代码和进展。
Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seamless integration with existing OpenAI SDK clients while leveraging the power of local ML inference.