verbatim-rag
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
22796 tools
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
A Markdown convention and linter for project docs written by AI and read by humans and agents
6-step Qwen-Image-2.1 on a node canvas, by @akhaliq
Twiga is a WhatsApp bot for Tanzanian educators.
Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions
💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.
AntNest 是一个采用蚁后 / 工蚁架构(或蜂后 / 工蜂)的 AI 编程助手。你可以把它想象成一个蚁群: 蚁后(本体):只负责思考、规划、决策。蚁后从不亲自执行任何命令。
记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)
A general-purpose terminal AI agent with traceable knowledge sharing and dispute resolution|面向终端的通用 AI 助手,可独立运行或参与团队协作,让 Agent 共享可检
SparseRead: token-efficient reading for AI agents. 读得更少,token 更省,证据不变。 Paper arXiv:2608.22237
Open decision and guard models, in your browser
A lightweight Gradio WebUI for stable-diffusion.cpp.
Connect your AI client to Ableton Live 12. Shape notes, instruments, effects and arrangements; compare audio before keeping a change. 474 tools across 57 domain
Modern ISO 8583 simulator with CLI, Python SDK, and interactive notebooks. Parse/build/validate messages at 180k+ TPS. Supports all major card networks and EMV
Local LLM inference on Xbox Series S and Series X in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by default),
🎬 Open-source animated architecture diagrams as code. Diagram-native DSL, 17 layout engines, Web Animations API, and MCP server for AI agents.
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets cove
Auditable bioinformatics workflow compiler: Catalog-bound planning, Workflow IR, and validated WDL 1.0.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automat
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, C
Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic research to investment
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integ
High-performance, high-precision, locally-fast-deployed Jev-class medical decision service on national medical exams — four readings, one routed decision, zero
Korea Investment & Securities Open API Github