LLM: open-source projects on GitHub
2095 repositories on LLM, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
PI-GO: AI AGENT FOR CODING
Pi-go is a Go implementation of an AI agent that understands your code and suggests edits in real time. The tool works as a CLI, integrates with any repository and suppor
★ 224 · GoOPEN GENI: SELF-HOSTABLE AGENT SERVICE
Opengeni — an open self‑hostable agent service for organizations, providing durable and replayable agent sessions, human approvals, and governed credentials. It runs in i
★ 224 · TypeScriptDARIO: CLOUD WITHOUT LIMITS
Dario is a local endpoint that mirrors the Claude Code format. Use your Claude Pro/Max subscription in Cursor, Cline, or Aider without paying for tokens.
★ 223 · JavaScriptSENPI — PI-MONO Fork with Extensions
Opinionated fork of pi-mono by badlogic with extension-first approaches. 222 stars on GitHub.
★ 222 · TypeScriptLEANKG CODE WITHOUT TOKENS
LeanKG helps write efficient Rust code without extra tokens, speeding up development and reducing load on LLM.
★ 222 · RustOPENAI TTS FOR HOME ASSISTANT
The openai_tts component for Home Assistant uses OpenAI Speech API (or any compatible endpoint) and outputs high‑quality speech. There is an optional chime before/after s
★ 222 · PythonBUSBAR: MANAGING AI AGENTS
busbar is the execution control plane for AI agents, controlling each model request, MCP tool call, A2A delegation, and subsequent action while preserving all native LLM
★ 222 · RustDEVOPS COCKPIT IN ONE WINDOW
opsdeck — free open-source tool for DevOps. Combines terminal with local AI, Kubernetes, SSH, databases, IDE with Git, alerts, notes and KeePass. Runs on Linux, Windows a
★ 222 · TypeScriptAI AGENTS FOR STOCK TRADING WITH NEWS BACKTESTING
A set of AI agents for trading US stocks with honest news backtesting: headlines replay at the minute of publication, orders fill at the next open. Includes a public LLM
★ 222 · PythonLLM Alignment Tuning
Automatic calibration of the language model's censorship layer via direct weight modification and the use of LoRA and MoE experts.
★ 221 · PythonNEURALINVERSE AI IDE
Open-source AI-native IDE featuring agentic coding, Power Mode, legacy code modernization, and firmware development.
★ 221 · TypeScriptCAMELID: LOCAL AI ON RUST
Camelid — a Rust‑native backend for local inference, compatible with models via evidence‑gated compatibility. Supports Apple Silicon, GGUF, Llama and other LLMs, runs ful
★ 221 · RustPEGAFLOW KV CACHE FOR LLM
Pegaflow — high‑performance KV‑cache storage for LLM inference. Supports offloading to GPU, caching on SSD, and cross‑node exchange via RDMA. Compatible with vLLM and SGL
★ 221 · RustUNIFIED DESKTOP FOR AI AGENTS
runjam unifies Claude Code, Codex CLI, and Gemini CLI in one window. Auto-detects agents, one-click install, unified chat, file explorer, terminal, and editor. Local-firs
★ 221 · RustAI4AI: 1135 PAPERS FOR AGI
Weekly updated collection of 1135 papers on benchmarks, harnesses, and agent architectures. Covers long-horizon agents and recursive self-improvement. Includes citation r
★ 221 · PythonREACHAT UI BLOCKS FOR LLM
reachat provides ready‑to‑use UI components for quickly building LLM‑based chat interfaces. Written in TypeScript and supports customization for any models.
★ 220 · TypeScriptOPEN SOURCE AI GATEWAY IN RUST
aisix — a single OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock. Supports routing, guardrails, caching, rate limits, and observability. 201 stars on GitHub.
★ 220 · RustON-DEVICE AI SDK KOTLIN
Llamatik is an on-device AI SDK for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). Supports LLM inference, Speech-to-Text, image generation, Agent Framework and
★ 220 · KotlinISOLATED DESKTOP FOR AI AGENTS
Agent-workspace-linux creates a hidden desktop and browser via MCP. AI agent performs GUI and web tasks without touching your real environment. Written in Rust.
★ 220 · RustOPEN GATE FOR LLM
OpenGateLLM — open-source unified interface for running and managing self-hosted LLMs. It lets you easily connect the models via the API and control their operations in o
★ 219 · PythonLLM TOKENOMICS: TOOLS TO SAVE
Curated list on AI token economics: costs, waste, and how to cut bills. Tools, benchmarks, papers, and ready configs for LLMs and coding agents. 206 stars on GitHub.
★ 219 · PythonGIT HOOK CHECKS YOUR CODE KNOWLEDGE
Git hook grip won't let you push changes unless you can explain your diff. Runs a quiz on your edits and works with Claude Code, Codex, and Cursor.
★ 219 · PythonFRUGON - LLM COST ANALYSIS
Free, local, and open LLM cost analyzer. See where your spend “leaks,” right on your machine.
★ 218 · PythonCODE GRAPH FOR AI
Graphmind — a local code intelligence system for AI assistants. It turns your repository into a knowledge graph that AI can query, navigate, and remember. Includes 25 rea
★ 218 · RustCHIASMUS — MCP SERVER FOR FORMAL VERIFICATION
Chiasmus — an MCP server that gives language models access to formal verification tools. It converts queries into formal specifications and generates proofs using Coq, Is
★ 218 · TypeScriptMAKERAI: AI OS FOR DELPHI
MakerAi is an AI operating system for Delphi, a fully native framework with RAG 2.0, autonomous agents, MCP protocol, and a universal LLM connector. Supports OpenAI, Clau
★ 218 · PascalAUTOPILOT FOR JOB SEARCH
AI agent hi really scans over 130 career pages each night, scores every job against your resume via an LLM (0‑100) and sends Telegram alerts. Automatically truly generate
★ 218 · PythonEMPEROR-AGENT: LOCAL AI WITH WEBUI
Emperor-agent is a local Emperor-style AI agent with Vue WebUI. Supports multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry. 203 stars on Git
★ 218 · TypeScriptCONNECT 18 LLMS TO COMMAND CODE
pi-commandcode-provider — custom provider for Command Code API. Provides access to 18 models: Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, Qwen. 215 stars on GitHub, writte
★ 218 · TypeScriptANUBIS: BENCHMARK LLM ON APPLE SILICON
anubis-oss — Swift utility for local LLM launch and benchmarking on Apple Silicon. It measures speed and accuracy of GPU inference, comparing results with CPU baseline an
★ 217 · SwiftMINIAGENT PLUGIN‑ORIENTED AGENT PYTHON
MiniAgent is a framework for creating AI agents in Python, with support for multiple LLMs, the MCP protocol, and skills. It allows plugging in plugins, saving sessions, a
★ 217 · PythonSKILLS FOR AI AGENTS IN PRODUCTION
Skills library for Claude Code agents. Ready modules for production tasks: code, files, API. Extensible architecture lets you add custom skills.
★ 217 · PythonAGENT FOR CODING AND RESEARCH
Open-source agent with local model support and isolated sandbox. Handles coding, research and routines without data leaks.
★ 217 · PythonGRADIENT DESCENT FOR AGENTS
Parallel framework for self-evolving agents. Parameters are agents, diffs act as gradients, aggregator as optimizer. Async Python architecture.
★ 217 · PythonOPENAGENTD - Local AI Agent OS
Self-hosted AI agent OS with streaming chat, tool usage, persistent memory, and multi-agent teams. Everything runs on your machine.
★ 216 · PythonCOGNIDB: SQL IN PLAIN ENGLISH
CogniDB lets you ask questions of your database in plain English and get precise SQL queries without needing to know code.
★ 216 · PythonTOKENIZER BPE FOR OPENAI
Tokenizer — BPE tokenizer for TypeScript and .NET for OpenAI models. Trains vocab, encodes and decodes tokens, compatible with tiktoken. Easily integrates into AI product
★ 215 · C#MCP SERVER FOR KICAD
MCP server for KiCad, connecting AI agents to schematics and PCB. Supports ERC/DRC validation, DFM checks, BOM analysis, and manufacturing prep. Edits require human appro
★ 215 · PythonLEARNING TO BUILD AI AGENTS
Systematic tutorial on building AI agents: LLM, RAG, tools, memory, multi-agent systems, LangChain, LangGraph, and RL. Daily arXiv updates.
★ 214 · HTMLSELF-HOSTED AI PLATFORM
nosia — a self-hosted Ruby platform for RAG and MCP AI agents. Run your own AI pipeline without relying on cloud services.
★ 214 · RubyCONFIGURATION CLAUDE CODEX
Configuration for Claude Code, Codex and multi‑agents: principles, hooks, skills and workflow templates. Provides ready‑made hooks and skills for AI‑assisted development.
★ 214 · PythonENTERPRISE GATEWAY FOR AUTONOMOUS AGENTS
Wirken — enterprise gateway for autonomous agents in Rust. Manages identity, isolates channels, stores secrets in vault, and keeps tamper-evident per-session audit logs.
★ 214 · RustLLM TRAINING ACCELERATION ON SUPERPOD
Framework for distributed LLM training with SuperPod topology awareness. Optimizes process placement and inter-GPU communication. Supports PyTorch and scales to thousands
★ 214 · PythonTAOS Self-Learning AI OS
Self-hosted auto-clustering AI-agent OS for your hardware: Raspberry Pi, Orange, Mac Mini, etc.
★ 213 · PythonINFERENCE GATEWAY: UNIFIED LLM
Cloud gateway that unifies local and cloud LLM providers: Ollama, OpenAI, Groq and others, built in Go.
★ 213 · GoOPENCODE COPILOT CHAT AI
opencode-copilot-chat gives access to 30+ AI models in GitHub Copilot Chat free via your own API key (BYOK). No Copilot Pro needed — everything works straight from your e
★ 213 · TypeScriptSTATEWAVE - MEMORY FOR AI AGENTS
Open-source memory runtime for AI agents with reproducible context bundles and provenance tags instead of retrieval on queries.
★ 212 · Pythonhaystack-core-integrations - SCALE HAYSTACK FAST
Additional packages for Haystack: components, document stores, and other tools extending its capabilities.
★ 212 · PythonTEMPORALSTORE FOR LLM CONTEXT
TemporalStore is an open-source Rust project designed for managing the context of large language models. It provides temporal functions for tracking context changes and r
★ 212 · PythonEFFICIENT AIGC: RESOURCES AND INSTRUCTIONS
This repo collects efficient AIGC works. It includes papers, docs, and codes for language and vision research. The project continuously improves and welcomes Pull Request
★ 212RAG ASSISTANT VISUALIZATION
The tool visualizes the RAG assistant workflow, showing data retrieval and answer generation.
★ 211 · PythonJIDO AI: ELIXIR AI LAYER
jido_ai — AI integration layer for Jido agents with LLM orchestration and reasoning strategies. Written in Elixir, already 201★.
★ 211 · ElixirSKRUN: DEPLOY AGENT SKILLS
skrun lets you deploy any agent skill as API via POST /run. It's an open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry and Mistral/Koyeb, ful
★ 211 · TypeScriptAI TOKENS UNDER CONTROL
TokenBar is an open-source cross-platform AI quota monitor. Tracks limits for Codex, Claude, Cursor and 47 more services on Windows, macOS, Linux, Android and iOS. Built
★ 211 · DartVERBATIM RAG: UNCHANGED SOURCES
Extracts exact source fragments with citations, using ModernBERT or LLM.
★ 210 · PythonSICLAW: AI Platform for SRE
A read‑only infrastructure diagnostics platform with AI analysis, security, and team collaboration.
★ 209 · TypeScriptGINI-AGENT: MEMORY AGENT
A TypeScript agent that remembers context and learns on the fly, making AI work more personalized and efficient.
★ 209 · TypeScriptLOCAL MULTIMODAL CHAT
Self-hosted chat with local LLMs (Ollama/OpenAI), supporting PDF RAG, image chat, and voice input via Whisper.
★ 209 · PythonOLLAMA SDK FOR .NET
Ollama SDK for .NET provides ready-to-use clients for working with Ollama models: chat, embeddings, and code generation. Supports .NET 6+ and offers a fully typed API.
★ 209 · C#ArcRift: Memory for AI Agents
Sync context from browser chats to local IDE agents via a local SQLite knowledge graph.
★ 208 · TypeScriptNew projects on this topic in Telegram
Telegram →