MemVanta
Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducible llama.cpp benchma
Compare 10,711 quality-filtered AI tools—LLMs, coding agents, image generators, and automation—using public popularity, activity, and licensing data.
Explore quality-filtered AI tools for chat, coding agents, image generation, RAG, and automation. Rankings use public popularity and project activity—not paid placements.
Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducible llama.cpp benchma
[ICML'26] Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation
A high-performance, local, offline-first AI memory system built in Rust
Open-source LLM Prompt-Injection and Jailbreaking Playground
A TypeScript client for running flows via the Langflow API
Detection of LLM-Generated Codes [ICSE2025]
A lightweight library for interacting with Google's Gemini API from C#/.NET including Microsoft.Extensions.AI support.
Cubicle: a live pixel-art office for your AI agents (Paperclip, Claude Code, Codex, Gemini CLI). See who works, who needs you, who failed; KPI board, Telegram a
ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-authored scenes to AI
ИИ для 1С-Битрикс: скиллы для Claude Code, Cursor и Codex, чтобы агент писал код по канону D7, а не legacy. 50 скиллов: ORM, контроллеры, кеш, безопасность, инф
📱 仿 iMessage 的 AI 角色扮演聊天 Web App(PWA)|群聊 · 朋友圈 · 世界书 · 语音/视频通话 · 主动消息 · 酒馆 SillyTavern 角色卡导入|支持 OpenAI 兼容接口 / Claude
🐙 Admin console for the OCTO platform — manage tenants, users, spaces, channels, and Lobster agents. Built with React, TypeScript, Vite & Ant Design.
Escouade, l'environnement de développement pensé pour les agents (ADE) : planifier, coder, relire et tester, livrer, avec des agents en parallèle. Windows, macO
为 DeepSeek Harness 打造:选中 AI 回答或思考内容,随时追问、学习、检查与纠偏。
A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from scratch, locally on
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent workflows (ReAct/Plan-Act/RePlan), long-term memory, and traceabl
From-scratch Llama 2-inspired Transformer in PyTorch for exploring tokenization, pre-training, and inference.
Cybara - Your agents. Your tools. Your runtime. Harness the power of AI
Consort keeps AI-written code clean and correct: a coordinated ensemble of role agents, spec-first and test-driven, driven by a deterministic state machine agai
RoleMule — One mule for every role. Self-hosted AI job companion. Paste a posting (or Chrome extension): five agents analyze the role, score fit, research the c
Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.
The hosted share target for crit - Your feedback loop with the agent.
A full-stack AI prompt library for discovery, structured authoring, safe imports, moderation, and shareable agents.
Glyph Studio (formerly Prevail): a private, local-first AI harness for your life. Part of the Glyph family.