Search results for "oss"
WebSocket client & server library, WAMP real-time framework
A Python framework for building reactive web-apps. Developed by Plotly.
A light-weight and flexible data validation and testing tool for statistical data objects.
Interface between LLMs and your data
CMake is an open-source, cross-platform family of tools designed to build, test and package software
SGLang is a fast serving framework for large language models and vision language models.
Tools to manipulate font files
Free, open-source SQL Server execution plan analyzer â cross-platform GUI + CLI with 30 analysis rules, missing index detection, SSMS extension. Built-in MCP server for AI-assisted plan review.
A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
AI agent skills manager for Claude Code, Cursor, Codex and more â install, sync, and manage skills from one desktop app.
Multi-agent code review mesh â orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch r
ARIS âïļ (Auto-Research-In-Sleep) â Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in â works wi
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Agent éĐąåĻįäļäļįš§åđģéĒčŪūčŪĄå·Ĩä―å° / Agent-powered graphic design workbench that uses HTML/CSS/SVG as the design medium, supporting vector-quality output, editable elements, multi-layer PSD export, lossless text ren
A high-throughput and memory-efficient inference and serving engine for LLMs
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.
ðĒ Open-Source Evaluation & Testing library for LLM Agents
Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI.
Ninja is a small build system with a focus on speed
Persistent memory for AI coding agents. Cross-session context, global knowledge, and autonomous task execution.
Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.
Markdown-native AI agent orchestrator. Write tasks in a kanban board, agents do the work.
The Context Optimization Layer for LLM Applications
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.
Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, 112+ MCP tools, 5-tier memory, A2A protocol, knowledge vault, voice, browser automation, Computer-us
Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimi
LlamaIndex is the leading document agent and OCR platform
A text-based user interface (TUI) client for interacting with MCP servers using Ollama. Features include agent mode, multi-server, model switching, streaming responses, tool management, human-in-the-l
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
Token-efficient navigation substrate for AI coding agents. Index code once and retrieve only the symbols you need.
Your AI assistant that never forgets and runs 100% privately on your computer. Leave it on 24/7 - it learns your preferences, helps with code, manages your health goals, searches the web, and connects
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
The agent environment for long-horizon work, continuity, and self-evolution.
Declarative Agent Orchestration. Ship while you sleep.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropi
Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI),
High-Performance Encrypted Database for .NET 10 | Embedded + gRPC Server | Vector Search âĒ GraphRAG âĒ Analytics
Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and
ðŠĒ Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. ðYC W23
å°įĢåļæģéĒåĪæąš + å ĻåæģčĶčģæåšŦ MCP server · Query Taiwan legal data from any MCP AI agent
High-scale LLM gateway, written in Rust. OpenTelemetry-based observability included
Multi-agent orchestration platform for Gemini CLI and Claude Code â 22 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and comp
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
âĨ AI Coding agent for the terminal â hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
Zero-dependency CLI for cross-model AI agent communication setup
Unify Claude Code, Codex, Cursor, and Gemini CLI with persistent context, governance, and multi-model debate. 186 MCP tools. 123 tests.
ð Drop-in tools that give AI agents reliable, permission-aware access to external systems.
ð Drop-in tools that give AI agents reliable, permission-aware access to external systems.
vMLX - Home of JANG_Q - Cont Batch, Prefix, Paged, KV Cache Quant, VL - Powers MLX Studio. Image gen/edit, OpenAI/Anth
Agent Sandbox is an E2B compatible, enterprise-grade ai-first, cloud-native runtime environment for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, an
One API for 25+ LLMs, OpenAI, Anthropic, Bedrock, Azure. Caching, guardrails & cost controls. Go-native LiteLLM & Kong AI Gateway alternative.
The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
This Guidance demonstrates how to streamline access to numerous large language models (LLMs) through a unified, industry-standard API gateway based on OpenAI API standards
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
ðĄ All-in-one AI framework for semantic search, LLM orchestration and language model workflows
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
An open-source harness for spec-driven code generation.
OllamaFreeAPI: Free Distributed API for Ollama LLMs Public gateway to our managed Ollama servers with: - Zero-configuration access to 50+ models - Auto load-balanced across global nodes - Free tier w
Official Repo of Moss
Recallium is a local, self-hosted universal AI memory system providing a persistent knowledge layer for developer tools (Copilot, Cursor, Claude Desktop). It eliminates "AI amnesia" by automatically c
Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, spe
A coding agent optimized to smaller LLMs
Curated list of the best truly open-source AI projects, models, tools, and infrastructure.
Dragon Brain â persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cur
RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.
Local-first Agentic Memory Layer for MCP Agents âĒ 25 tools âĒ Hybrid search (FTS5 + vector + MMR) âĒ GDPR âĒ 100% local
ð Next Generation Multi-tenant AI One-Stop Solution. Builtin Admin & Billing System. Enterprise-Grade Unified LLM Gateway Support for 200+ Models And 35+ Providers, Load Balacing w/ Priority-base Rou
ð LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI), automatic hardware detection (optimiz
A universal CLI for Weaviate, Milvus, Chroma, Qdrant, and other vector DBs to help view, list, create, delete, and search collections and documents in collections for development, test, and debugging
A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other
Multiplatform system monitoring tool using Cosmopolitan Libc
Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine â zero data sent to external services.
AI-powered multi-agent system that transforms Telegram into an intelligent automation hub â routing user intent across vision, browser, desktop, and code agents using dynamic model orchestration.
Local AI anywhere, for everyone â LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. No cloud, no subscriptions.
A command-line interface tool for serving LLM using vLLM.
SDK to build Agents in rust. Build and manage complex, self-correcting agent teams. Launch multi-agent systems via configuration files or using an Agent Factory. It's the robust framework for orchestr
ð Connect AI agents with a shared memory system to keep conversations seamless and information persistent across sessions.
Python LLM-RAG deep agent using LangChain, LangGraph and LangSmith built on Quart web microframework and served using Hypercorn ASGI and WSGI web server.
ð Enable real-time exploration of GitHub repositories with this high-performance Model Context Protocol (MCP) server built in Rust.
ð Build a robust MCP gateway platform to enhance your Plex experience with seamless integration and reliable performance.
Open infrastructure/control plane for Unchained
ðĪ Generate tailored AI training datasets quickly and easily, transforming your domain knowledge into essential training data for model fine-tuning.
Gossip mesh hub â WebSocket relay for AI agent communication