MemFree - Hybrid AI Search Engine & AI Page Generator
AI ओपन सोर्स प्रोजेक्ट
GitHub पर देखने लायक चुनिंदा AI ओपन-सोर्स प्रोजेक्ट: बड़े भाषा मॉडल, एजेंट, RAG, लोकल डिप्लॉयमेंट, इमेज और आवाज़… अब तक कुल 1047 प्रोजेक्ट।
Cloudflare, Vercel, Netlify आदि पर मुफ़्त डिप्लॉय होने वाले प्रोजेक्ट चाहिए? देखें मुफ़्त डिप्लॉय चयन
सभी 1047🧠 बड़े भाषा मॉडल 26🤖 AI एजेंट 164🧩 ऐप डेवलपमेंट प्लेटफ़ॉर्म 23📚 RAG और नॉलेज बेस 46💬 चैट इंटरफ़ेस और क्लाइंट 41🖥️ लोकल इन्फ़रेंस और डिप्लॉयमेंट 87👨💻 AI कोडिंग 99🛠️ डेवलपमेंट फ़्रेमवर्क और SDK 47🔌 MCP और टूल इकोसिस्टम 34🎨 इमेज जनरेशन 25🎬 वीडियो जनरेशन 17🎙️ आवाज़ और ऑडियो 44👁️ कंप्यूटर विज़न 28📄 दस्तावेज़ पार्सिंग और स्क्रैपिंग 24🗄️ वेक्टर डेटाबेस 25🏋️ ट्रेनिंग, फ़ाइन-ट्यूनिंग और MLOps 75🧪 मूल्यांकन, ऑब्ज़र्वेबिलिटी और सुरक्षा 81🚪 API गेटवे और प्रॉक्सी 12🔎 सर्च और डीप रिसर्च 15⚙️ डीप लर्निंग लाइब्रेरी 56🏷️ डेटा और एनोटेशन 31🔬 उद्योग और विज्ञान के लिए AI 34⚡ उत्पादकता टूल 13
A benchmark built to evaluate and improve agent capabilities for supporting legal work.
KaibanJS is a JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach.
Platform for AI-powered software engineers
💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.
An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.
Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter
🌎💪 BrowserGym, a Gym environment for web task automation
Quilt is a Scientific Data Management Platform on AWS that helps teams and AI find, trust, and reuse data through deeply versioned, context-rich data packages.
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Whisper command line client compatible with original OpenAI client based on CTranslate2.
Scalable and memory-optimized training of diffusion models
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
LiveBench: A Challenging, Contamination-Free LLM Benchmark
A free, open-source Obsidian plugin that makes your vault smarter: better search, an interactive knowledge graph, and an AI assistant that knows your notes.
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
Hopsworks - Data-Intensive AI platform with a Feature Store
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers.
AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
Coding agent memory for Claude Code, Codex, Cursor and 39 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.
AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, gu