LLM: open-source projects on GitHub
2094 repositories on LLM, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
AIDA: AI PenTester
AIDA turns any LLM into an autonomous pentester: you set the scope, the agent finds vulnerabilities, you get a report.
★ 513 · JavaScriptMEDIAPIPE4U-PLUGIN: FAST RECOGNITION
Plugin for MediaPipe integration: ready-made pose, gesture, and face models. Simplifies adding AI features to any projects.
★ 512Clawwork — Your OpenClaw Second Screen
A client for OpenClaw with a multi‑session desktop. Connect ClawWork to your OpenClaw and boost productivity tenfold!
★ 510 · TypeScriptMATHCODE: MATHEMATICS CODES ITSELF
MathCode is a Shell agent that generates mathematical code and solves problems in real time. Ideal for researchers and engineers.
★ 509 · ShellAI Agent Platforms List
A curated repository of open AI agent platforms: AI teammates, framework builders, workflow automation, browser and code agents, with license information.
★ 509 · AstroMASTER-SKILL: Buddhist AI Framework
Framework for creating a Buddhist AI persona based on FoJin, with accuracy verification, boundary awareness, and runtime readiness.
★ 508 · PythonAI LAWYER FOR CONTRACTS
AI skill for contract review: CUAD risks, benchmarks, and ready redlines for lawyers. Works with Claude Code, Codex, Cursor, and 26+ tools.
★ 508DANUS: Agents of Mathematics and Reasoning
The project combines reasoning agents with a fact‑graph memory to solve complex mathematical problems.
★ 507 · PythonREAD WITH AI: SMART READER
read-aware — an e-reader with a self-evolving AI agent that remembers your progress across all books and suggests contextual notes. Plugins extend format support, cloud i
★ 505 · TypeScriptNADIRCLAW: LLM Routing for Savings
Routes queries to cheap local models and premium LLMs, saving 40‑70% on API costs.
★ 504 · PythonAGENT — CREATE LLM AGENTS
The agent library lets you create LLM agents using XState finite state machines, guaranteeing predictable behavior and simple integration in any project.
★ 504 · TypeScriptPERSONAL AI ASSISTANT WITH MEMORY
AI assistant that adapts to you: remembers context, takes initiative, and works in macOS, Telegram, and Slack. ⭐ 503
★ 503 · TypeScriptMANIFOLD: AGENTS FOR AUTOMATION
Manifold is an experimental platform where teams of AI assistants automate complex multi-task processes. Written in Go and has already gained 498 stars.
★ 503 · GoManimCat: AI Math Animations
ManimCat converts natural language descriptions into high-quality Manim animations with LaTeX support and automatic code correction.
★ 502 · TypeScriptCREATE VIDEO WITH AI DIRECTOR
Frametell turns ideas and materials into vivid explainer videos thanks to an AI director agent. It works fully locally and supports any model.
★ 502 · TypeScriptAI DIAL: UI FOR LLM
An open web interface for AI DIAL — a platform for communicating with language models. A convenient chat with support for multiple providers.
★ 501 · TypeScriptFLIDE: INSTANT DECISION INFERENCE
Flide is a decision model inference engine with CUDA support. Provides deterministic inference for Gemma and other models in microseconds. Ideal for AI agents requiring s
★ 501 · PythonOPENVLHARNESS: VISUAL AGENTS WITH MEMORY
OpenVLHarness is a framework for evaluating and building visual agents with multimodal memory. It supports real-world tool-use scenarios and complex reasoning chains.
★ 499 · PythonGrokBot Catalog
A bilingual catalog of 361 verified GrokBot bot links with JSON schema, CI, and site search.
★ 498 · PythonATHENA-PUBLIC OS FOR AI AGENTS
Linux operating system that gives AI agents persistent memory, autonomy, and time awareness. Manage state, rent intelligence.
★ 497 · PythonToken Tracker for CLI Agents
Tracking token usage in 16 AI agents. A local application with a dashboard, widgets, and a macOS menu bar.
★ 496 · JavaScriptYZMA: Local LLM in Go
Integration of llama.cpp into Go applications for local inference with hardware acceleration. 496 stars on GitHub.
★ 496 · GoPANTHEONOS: Data Science Agent
PantheonOS is a modular framework for building distributed AI agents, simplifying data pipelines and experiments.
★ 496 · PythonQWEN3.6-27B ULTIMATE VERSION
Fully uncensored, enhanced version of Qwen3.6-27B with NVFP4 and DFlash speculative decoding.
★ 495 · PythonFLOCK — AUTONOMOUS AI TEAM
A Go bot that creates a full‑fledged AI developer team for autonomous work on projects. 745 stars on GitHub.
★ 495 · GoBUILD AI PHONE AGENTS LOCALLY
Lampline lets you build AI phone agents on your computer and test them with an AI caller. Open source, runs free without API keys, cents per call with your own keys. Impo
★ 495 · PythonAWESOME JEV GALLERY: PAPERS AND REPRODUCTIONS
Awesome Jev Gallery — collection of articles, open reproductions and independent evaluations of System One and Jev models. Includes links to code, calibration metrics and
★ 493 · JavaScriptAWESOME JEV USE CASES
List of 74 TypeSafe AI Jev demos ranked by likes, with 150+ repos, limits, costs and API examples. All under CC0 license. Includes AI guardrails, AI router and classifica
★ 493OPENACCOUNTANTS: AI Accounting
Over 1,000 verified accounting skills for AI agents, covering 192 jurisdictions and all U.S. states.
★ 492 · PythonAwesome MLSecOps Resources
A curated collection of tools, articles, and resources on machine learning security and MLOps.
★ 492TOOL LEARNING SURVEY FOR LLM
Repository with comprehensive Tool Learning survey: taxonomy, benchmarks, and LLM tool integration methods. 493 GitHub stars.
★ 492Agency: Minimal Framework for Agents
Fast and minimalistic framework in Python for building agent systems. 486 stars on GitHub.
★ 491 · PythonLLM2Jev:DECISION MODELS FROM TEXT
The LLM2Jev project converts the local language models into the structured decision models of the Jev style. It outputs the results from the text and images solely via pr
★ 491 · PythonCHATTS LLM FOR TIME SERIES
ChatTS — the first LLM trained to understand and reason about time series, presented at VLDB'25.
★ 490 · PythonCAD SYSTEM WITH AGENTS FOR CADQUERY
Desktop app for creating parametric 3D models via CadQuery code. An AI agent writes Python code, SOMA builds the model and shows the result in a 3D viewer.
★ 490 · TypeScriptLLMFEEDER: One-click LLM
The browser extension turns any web page into clean Markdown and copies it to the clipboard — perfect for quickly feeding context to your LLM.
★ 488 · JavaScriptALPHASIFT - AI Engine for Stocks
A full-featured LLM-based engine for stock screening with ranking, risk assessment, and auditable analytics. 219 stars on GitHub.
★ 487 · PythonAUTOMATING SCIENTIFIC PAPERS IN LATEX
An agentic framework for creating arXiv-ready ML/AI papers with automatic citation checking and a controlled LaTeX workflow.
★ 487 · TeXVLLM ON C++: POWERFUL SOLUTION
vllm.cpp is an open-source C++ engine, fully compatible with vLLM: continuous batching, paged KV-cache, GGUF support, RadixAttention and cache-aware scheduling. 447★, bui
★ 487 · C++UNIVERSAL AI AGENT ON BEDROCK
bedrock-engineer — universal AI agent on Amazon Bedrock. Creates and edits files, executes commands, searches the web, uses knowledge base and multi-agents. Supports imag
★ 487 · TypeScriptSIGMAP: 97% Token Reduction
Sigmap reduces token usage in AI coding sessions by 97% without external dependencies, supporting 31 languages and featuring a built-in MCP server.
★ 486 · JavaScriptPR-COCKPIT: LOCAL AI REVIEWER FOR PR
Local AI reviewer powered by Claude and Codex. Reviews code in isolated worktrees, GitHub comments appear only after your approval.
★ 486 · TypeScriptCORDUM - Manage AI Agents
Cordum is an open control plane for AI agents: pre‑execution policy, approval gates, and audit trail. Compatible with LangChain, CrewAI, MCP.
★ 485 · GoDetto: No-Leak Meetings
Detto is a macOS app for recording meetings, dictation, and a local knowledge base without data leaks.
★ 484 · SwiftCOMMAND CODE FOR DEEPSEEK HARNESS
The Command Code provider plugin for DeepSeek Harness (dsh) offers access to the Command Code model, a live model catalog, and plan‑aware model selection. It supports adj
★ 484 · TypeScriptSOCIAL COACH FOR EQ
SocialCoach — your personal EQ coach. Through role‑play with AI and instant feedback you practice communication and conflict resolution. Works using TypeScript and LLM.
★ 484 · TypeScriptSKILLS INTELLIGENT VISUALIZATION
skills — intelligent data visualization system based on LLM. Converts natural language queries into ready interactive charts without code.
★ 484 · PythonFLYTO-CORE: AI AGENT ENGINE
Open-source engine for executing AI agents with 412 modules, native MCP support, queues, versioning, and usage measurement.
★ 483 · PythonGERBIL: Local LLMs on Your PC
Desktop app for running large language models right on your computer. No cloud, no subscriptions — full control over AI.
★ 482 · TypeScriptCOMPLETE LLM INFERENCE GUIDE
A collection of best practices, tools, and examples for efficient inference of large language models using TypeScript.
★ 481 · TypeScriptLOWFAT - TRIMS COMMAND NOISE
Rust utility that removes noise from command output and saves tokens. Ideal for AI agents and developers.
★ 478 · RustSOURCEWEFT: OPEN AI WORKING STATION....
SourceWeft — open-source self-hosted alternative to ChatGPT and NotebookLM with agents, skills, MCP and a cited knowledge base. Use your models and infrastructure, gettin
★ 477 · TypeScriptWEBSITE RECONSTRUCTION BENCHMARK FOR AGENTS
Benchmark for evaluating the ability of AI agents to reconstruct full-featured websites through browser exploration. Contains 70 tasks with 46,916 hidden test cases for v
★ 476 · PythonLINGHUN - Artificial Intelligence for Code
Linghun is an AGI-oriented code execution environment, resistant to hallucinations, based on evidence, tools, memory, and verification.
★ 475 · TypeScriptPUPPETMASTER - AGENT SWARM MANAGEMENT
Puppetmaster provides a management plan for resilient agent swarms: subprocesses, leases, artifacts, and deterministic state stitching.
★ 475 · PythonWORKER-VLLM: POWERFUL LLM DEPLOYMENT
Runpod worker template for deploying LLM via vLLM — quick start and scalable operation.
★ 474 · PythonNEXT-GEN JAVA AI FRAMEWORK
solon-ai is a powerful Java framework for building AI applications with LLM, RAG, MCP, and agent support. Compatible with Java 8–25 and SpringBoot.
★ 473 · JavaDESIGN-STUDIO: AI DESIGNER WITHOUT CODE
Open-source no-code builder on TypeScript, where LLM/GPT meets a flexible graph for fast dialogues and automations.
★ 473 · TypeScriptPARSEBENCH: AI AGENT EVALUATION
ParseBench is a benchmark for evaluating the quality of document parsing by AI agents. It allows comparing models on real-world datasets.
★ 472 · PythonBLOCKRUN-MCP: LIVE DATA FOR AI
Search, research, markets, crypto, Twitter — all via AI agents. Pay-per-use via x402 micropayments.
★ 471 · TypeScriptNew projects on this topic in Telegram
Telegram →