Paid vs. Free subcategories
infiniflow/ragflow
A question-answering system built on a document collection, with the sources shown beside every answer.
musistudio/claude-code-router
One local address that many coding assistants can talk to, pointed at whichever model the operator chooses.
iver56/audiomentations 💎 hidden gem
Spoils sound recordings on purpose, 39 ways, so a model trained on them copes with real rooms.
deepset-ai/haystack
A Python framework for joining language models, document search and tools into one working pipeline.
Giskard-AI/giskard-oss
A Python library that writes tests for language-model programs and tries to break them on purpose.
EleutherAI/lm-evaluation-harness
Runs standard question sets against a language model and reports the scores.
hummingbot/hummingbot
A free framework for writing and running automated trading programs on cryptocurrency exchanges.
janhq/jan
Downloads and runs language models entirely offline as a desktop application, and opens a local server other programs can use.
mudler/LocalAI
Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.
Mintplex-Labs/anything-llm
One program that reads your documents and answers questions about them, with the model running locally if you want.
NousResearch/hermes-agent
A self-hosted assistant that runs commands, remembers past work and answers through six chat platforms and a terminal at once.
NVIDIA/NeMo-Guardrails
Puts rules you write around a language model's input and output, and enforces them before the answer reaches anybody.
dottxt-ai/outlines
Forces an AI model's answer into a shape you define, while the answer is being produced.
magnitudedev/magnitude
It measures the machine, tunes itself to that hardware, then runs open AI models locally.
vectorize-io/hindsight
A memory store for AI agents that keeps what matters across sessions instead of replaying the whole history.
langgenius/dify
A self-hosted workbench for building AI applications from a visual canvas, with document search and model switching built in.
BoundaryML/baml
A small language for describing what a model should return, and checking that it did.
opendatalab/MinerU
It converts PDFs into clean Markdown or JSON, keeping headings, tables, equations and reading order.
AnswerDotAI/rerankers 💎 hidden gem
One interface in front of every common reranking model, so swapping one for another is a one-word change.
freqtrade/freqtrade
A crypto trading bot that runs on its owner's machine, with testing on past prices and pretend-money trading built in.
lobehub/lobe-chat
A self-hosted place to run and supervise several AI assistants, formerly the chat interface LobeChat.
mem0ai/mem0
A memory layer that lets an AI application remember a person between separate conversations.
huggingface/lighteval 💎 hidden gem
Runs standard public tests against a language model and reports the score.
promptfoo/promptfoo
A test runner for prompts: you describe a good answer once, and it grades every model against it.
open-webui/open-webui
A private web page for talking to AI models, with accounts and document upload.
ggozad/oterm 💎 hidden gem
A chat window for AI models that runs in a terminal and keeps past conversations.
stanfordnlp/dspy
It improves the instructions sent to an AI model by measuring the answers instead of guessing.
segment-any-text/wtpsplit 💎 hidden gem
Splits text into real sentences in 85 languages, even when the writing has no punctuation.
microsoft/markitdown
Converts PDF, Word, PowerPoint, Excel, HTML, images and audio into Markdown in one command.
vibrantlabsai/ragas
Scores how good a retrieval-based AI answer is, so a change can be shown to have helped or hurt.
langfuse/langfuse
A platform that traces language model calls, versions the prompts, and scores the output.
pemistahl/lingua-py 💎 hidden gem
A Python library that detects which of seventy-five languages a piece of text is written in.
cheshire-cat-ai/core 💎 hidden gem
A ready-made assistant service with document search, a plugin system and a chat connection included.
datalab-to/marker
A command-line converter that turns PDFs into Markdown or structured data with high accuracy.
MinishLab/vicinity 💎 hidden gem
A small Python library giving one interface over several nearest-neighbour search methods.
shap/shap
A library that assigns each input feature a contribution to each individual model prediction.
optuna/optuna
A framework that searches for good parameter values instead of trying every combination.
HKUDS/LightRAG
A retrieval system that builds a network of things and relationships out of documents, then answers questions against it.
TutteInstitute/datamapplot 💎 hidden gem
A Python library that draws readable, labelled maps of text collections.
TutteInstitute/toponymy 💎 hidden gem
A library that writes readable names for groups of text, at every level of a tree.
567-labs/instructor
Makes a language model return data in a declared shape, and retries automatically when it does not.
BerriAI/litellm
A gateway that puts a hundred or more model providers behind one interface, with spend tracking and limits.
apple/embedding-atlas
Apple's interactive embedding map with automatic cluster labelling — worth studying as a design reference for an overview screen rather than adding as a dependency.
LibreTranslate/LibreTranslate
Self-hosted machine-translation API — removes the per-character meter from running a bilingual site.
x-tabdeveloping/turftopic 💎 hidden gem
Five families of topic model behind one scikit-learn-style API — the head-to-head against BERTopic in one afternoon.
docling-project/docling
A document parser that turns PDFs, office files, images and audio into clean structured text.
MaartenGr/BERTopic
A Python library that groups documents by meaning and labels each group with its distinguishing words.
feyninc/chonkie
Focused text-chunking library — semantic and recursive splitters that respect message boundaries, so subtopics come out clean.
microsoft/graphrag
A pipeline that builds a knowledge graph from documents and answers questions from nested cluster summaries.
MinishLab/model2vec 💎 hidden gem
Distils a sentence model into a static lookup table, so producing embeddings needs no graphics card.
AI-WorkDeck/aiworkdeck
Open-source workspace for professional document AI: reviewable agent edits, source-linked work, three-way document merges, and an extensible plugin runtime. Starting with legal work.
AnttiHero/lavern
An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 10-pass verification loop. Apache 2.0.
browseros-ai/BrowserOS
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
bytedance/deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
bytedance/UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
ChatGPTNextWeb/NextChat
✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go saves you more. Available on Web, iOS, macOS, Android, Linux, Windows.
CherryHQ/cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
ChuqingShi/CaseBoard
AI-powered personal injury legal case management dashboard with document intelligence and role-based workflows, built at the 2026 Law-Di-Gras Applied AI Hackathon.
comet-ml/opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
conductor-oss/conductor
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
coze-dev/coze-studio
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
eigent-ai/eigent
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
evolsb/claude-legal-skill
AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.
Fosowl/agenticSeek
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.
freelawproject/courtlistener
A fully-searchable and accessible archive of court data including growing repositories of opinions, oral arguments, judges, judicial financial records, and federal filings.
future-agi/future-agi
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
Future-House/paper-qa
High accuracy RAG for answering questions from scientific documents with citations
FuturixAI-and-Quantum-Works/Prism-Legal-OS
Open-source legal AI for contract analysis, legal research, and litigation
h2oai/h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
Helicone/helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
HKUDS/nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
invoke-ai/InvokeAI
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
jordan-gibbs/hyperresearch
Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
k2-fsa/sherpa-onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
kandinskylab/kandinsky-6
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Kiln-AI/Kiln
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
Klotzkette/claude-fuer-deutsches-recht
⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u.a.) – inzwischen verbessert und im Alltag getestet, aber weiterhin Experiment. Bitte selber ausprobieren, Issues/PRs willkommen! Keine Rechtsberatung. Mandatsgeheimnis (§§ 203/204 StGB, § 43e BRAO), DSGVO, US-Transfer, KI-VO & Co
langflow-ai/langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
latitude-dev/latitude-llm
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
LearningCircuit/local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
LibreChat-AI/LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
linshenkx/prompt-optimizer
An AI prompt optimizer for writing better prompts and getting better AI results.
microsoft/magentic-ui
MagenticLite is an experimental agent that works across the browser and local file system
microsoft/promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
mlflow/mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
munibqasim/agentic-medical-extraction
Multi-agent pipeline that turns scanned hospital charts into structured, confidence-scored clinical chronologies
mverab/eGEOagents
Open-source Generative Engine Optimization (GEO) & Answer Engine Optimization (AEO) toolkit — optimize content to rank in ChatGPT, Perplexity, Gemini & Claude. AI SEO / LLM SEO. CLI, Claude Code, MCP.
nanobrowser/nanobrowser
Open-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks.
OpenBMB/VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
openlit/openlit
OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.
OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
oumi-ai/oumi
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
pathwaycom/serviette
A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
pezzolabs/pezzo
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
QwenLM/Qwen-Image
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
SetCalc/personal-injury-verdicts-settlements-data
Open dataset of 17,611 US personal injury verdicts and settlements, including 4,971 car accident results: state, year, case type, injury, and amount for every record. CC BY 4.0, by SetCalc, the free settlement calculator.
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
simstudioai/sim
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
stanford-oval/storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Tencent-Hunyuan/HunyuanImage-3.0
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
traceloop/openllmetry
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
u14app/deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
unslothai/unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Vaquill-AI/ms-word-addin
Open Source Legal AI assistant for MS Word as Plugin - contract review, playbooks, drafting, and legal research task-pane add-in.
vladmandic/sdnext
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
YichiZ/ai-lawyer
Ontario personal-injury law research guide: RAG where every quote is checked in code and every answer is human-reviewed
zhayujie/CowAgent
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
No repository in this area carries every tag you picked.
Get the next edition in your inbox
A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.
No tracking pixels. One click to leave. The archive stays free either way.
We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.
Suggest a repository
Any public GitHub repository, any size. If it is your own, that is welcome too. We read every suggestion, and some picks are made at random, so stars do not decide. Whatever we pick goes through the same checks as every other entry, and the review is written either way.
Thanks — it is in.
Every suggestion is read. The ones we pick appear in an edition, credited to you if you left a name.