401.Gen-Verse / DiscoveryRSI
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
- recursive-self-improvement
Ranked by Attention Score: stars gained over the last 7 complete days
401–500 of 520 by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
The UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles.
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
A guidance language for controlling large language models.
Pretrained models for TensorFlow.js
OCR & Document Extraction using vision models
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
ChatGPT Native Application (Windows, Mac, Android, iOS, and Linux)
Dadbod Grip turns database tables into editable Vim buffers, with schema browsing, staged mutations, generated SQL, relationship navigation, and cross-database federation inside Neovim.
Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your machine.
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Question and Answer based on Anything.
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Large Language Model Text Generation Inference
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Chat with (and visualize) your codebase
Agentic Chat Interface directly in Neovim with ACP providers from Claude-Code, Gemini, Codex, OpenCode, and Cursor-agent
Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
A 1:1 Replica & 100% Open Source Claude Desktop
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
Install Tiledesk on your server using Helm for Kubernetes orchestration and Docker Compose for running multi-container Docker applications. Tiledesk provides an open-source solution comparable to Voiceflow, empowering you to create sophisticated LLM-enabled chatbots that seamlessly transition interactions to human agents when needed.
TranslatedAn enterprise-grade desktop AI Agent workbench that lets skills, knowledge, and tasks work together in one place.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Claude Code skill for naming products, SaaS, and brands. Metaphor-driven naming that avoids AI slop.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
Topic Modelling for Humans
Unified framework for building enterprise RAG pipelines with small, specialized models
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
Translated100+ Chinese Word Vectors
Official inference library for Mistral models
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
IoT Platform Framework
Build LLM-powered applications in Ruby
repository for Publicly Available Clinical BERT Embeddings
Real-time observability of claude code sessions & multi-agents.
The visual communication layer between humans and AI agents. Capture, annotate, render diagrams, and organize with AI — powered by Electron and Ollama. macOS & Linux.
Learn Claude Code by exploring it as it was designed - interactive IDE-style docs for commands, MCP, skills, CLAUDE.md and more.
Official library for RaBitQ vector quantization and approximate nearest-neighbor search, in C++ and Python.
A view for display markdown text.support markdown streaming like gpt&claude&gemini&deepseek
Feather agent harness, training integrations, and evaluation tools for knowledge work
OpenScribe is an open-source AI scribe that records patient encounters and generates structured clinical notes automatically. You keep full control over data, workflows, and patient privacy with no vendor lock-in.
🔍A cutting edge context aware GraphQL API fuzzing tool!
ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.
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.
A browser bookmarklet for exporting conversations with ChatGPT as markdown files.
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.
Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools.
Autonomous multi-agent framework to optimize scientific software
Embedded single file SQL database written in Golang
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
Self-hosted AI-assisted CTI-to-detection workbench for ATT&CK mapping, IOC/CVE intelligence, Threat Radar, malware triage, Attack Simulation, and SIEM validation.
Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
A detective for your data. Zero-config data quality monitoring — works with dbt, Postgres, BigQuery, Snowflake. No YAML.
The open-source map of the AI developer tooling ecosystem
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
TranslatedChatGLM3 series: Open Bilingual Chat LLMs
A collection of libraries to optimise AI model performances
⚡️ OpenAI PHP for Laravel is a supercharged PHP API client that allows you to interact with OpenAI API
Experimental toolkit for auto-generating codebase documentation using LLMs
🤖 A powerful, lightweight JavaScript library + interactive CLI for ChatGPT
Supercharged experience for multiple models such as ChatGPT, DALL-E and Stable Diffusion.
🦎 A lightweight, streaming-native, multi-protocol gateway for AI, APIs, and real-time data. Route LLM requests across providers, govern MCP tools, and connect Kafka, MQTT, and HTTP through one high-performance engine with shared security and observability.
Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers
Turn messy, real-world HTML into clean Markdown, from every major language.
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
Delicious diagnostic debugging in Neovim 🤤
OpenAI (and DeepSeek, Azure OpenAI, YandexGPT, Ollama, GigaChat, Qwen) API wrapper for Delphi. Use ChatGPT, DALL-E, Whisper and other products.
TranslatedSo powerful in function, yet so simple in code
TranslatedChat Answer is an open source app based on ChatGPT.
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
ESP32 using MicroPython meets LoRa and LoRaWAN.
A minimalistic C++ Jinja templating engine for LLM chat templates
AI agents can now write 99% of the code. This changes what it means to be a developer. Our role shifts to knowing "what good looks like". To do that, we need completely new developer tools. Tendril is what replaces your IDE in an agentic era.
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
Audit and fix your Mac's security in one command. No agent, no signup, open source.
Examples and code snippets demonstrating common ways of integrating Neon with various frameworks and languages.
A JavaScript library for display ads in React applications.
MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
Generates Conventional Commit messages with AI. Supports OpenAI, Ollama, and Gemini.
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
Gemini CLI wrapper to serve Gemini models through an OpenAI-compatible API
Run scripts, explore your genome, and get personalized explanations — all in natural dialogue.