Showing 30 of 5,113 · Category: LLM
Transparent OpenAI-compatible router with exact-model discovery, streaming, Prometheus metrics, and Grafana dashboards.
Official code for paper "Tailoring the Quantization Space for 1-Bit KV Cache Compression"
Thee Pori (தீப்பொறி): open-source AI coding agent to build and run a software factory from your terminal. Claude, OpenAI, and offline models via Thinai.
DSH 插件：生成式界面 / Generative UI for DeepSeek Harness。模型写声明式 DSL，无 DOM Worker 沙箱里执行，宿主用原生 DOM 画成真界面；另有一条自包含文档的逃生舱。原地改写、版本历史、跨重启可 patch。对标 ChatGPT Intelligent UI 与 Claude Artifacts。
Built on REA (Reverse Engineer Anything): dissect two projects, fuse their capabilities, and grow a brand-new verified creature.
Claude (or any LLM) acts as the whole app instead of writing it: try an idea by hand in minutes, then turn it into a spec and a build plan.
Escreva uma issue, receba um PR testado: Claude Code e Codex programando no seu repositório em salas Docker isoladas, com verificação independente. Self-hosted, zero dependências npm.
Claude Code mod: control autocompaction content from the TUI natively.
Let an AI agent work on your existing Flutter screen with the user, over AG-UI. It calls your own methods, keeping human in the loop conveniently.
从零手搓的 AIGC 内容生产 Agent：在终端里对话，把一句创意做成短剧成片、抖音短视频、广告片和海报。自研 harness：人审挂起、资产血缘、整批报价、质检门、预算护栏
Several AI coding agents (Claude, Codex, Gemini, Copilot, Cursor) in one room inside VS Code, with rooms, DMs and project guardrails.
Local LLM gateway: Google accounts and subscription quotas, API key profiles, auto-routing, Claude Code / Codex client setup (Windows app + CLI)
High-performance CLI & TUI repository packer for LLM prompts. Sub-15ms execution, zero runtime dependencies.
Self-hostable AI token pools — govern your org's AI usage with per-member keys, quotas, and leak detection; or deposit surplus credits into a Solana-settled marketplace.
MCP server for VRoid Studio. Lets AI agents create and edit characters in the editor — choose presets, tune sliders and colors, frame the camera, and save. Drives the editor's own API through a BepInEx/IL2CPP plugin: no mouse or OCR automation; works with the window minimized
Vietnamese-first self-hosted RAG on internal documents — Spring Boot + FastAPI + Next.js, hybrid dense/sparse/graph retrieval. DX-OS Open-Core entry (OLP 2026), Apache-2.0.
Give your AI agent the web as an API. MCP server + skill for Claude Code, Codex & Cursor: self-healing scrapers for Google Maps, Amazon, Instagram, X, LinkedIn & more. Firecrawl- and Apify-compatible.
Open-source cross-platform voice dictation: local or BYOK transcription, AI refinement, hands-free wake word
A coding agent you run on your own machine, with the models you choose: desktop (Linux, Windows), headless server and Android, with signed self-updates.
EZ AI — Local AI made easy: Windows command center for local AI apps, model library, and coding agents.
Autonomous multi-agent AI intelligence brief system powered by LangGraph, ArXiv & RSS feeds.
Windows 桌面端 AI 编程助手——接入你自己的模型服务商，在工作目录里安全地读代码、跑命令、改文件；支持生图/视频/音乐与多模态识别。Tauri 2 + React 19 + Rust
Indian-market research terminal: live NSE/BSE quotes, index coverage, rule-based quant screen, and a TradingAgents-style multi-agent desk (analysts -> bull/bear -> risk -> portfolio manager) that ends in a rated, sized trade call.
Local Hybrid System-One Decision Engine (JevCompat 32/32 MUST, AnyJev L0 Prefill, StartLux Cascade, OpenJev-RLCD² Trainer, Zero-Shot AI Safety Guardrails)
OpenCode on DeepSeek Harness — DSH plugin that keeps OpenCode Zen + Go free-tier models working: session affinity, gateway origin headers, and tool-schema fallback.
让任何 AI 大模型用代码做出好看的视频：Agent Skill + film CLI，九种技术栈（Canvas/GLSL/Three.js/p5.brush/GSAP/Remotion/Manim/Blender…），代码配乐、AI 旁白、自动字幕、逐帧审片、一键出片。支持 Claude Code、Codex、WorkBuddy 等 Agent。
Shared handoff file for AI coding agents: tracks unpushed, unrestarted and half-done work across sessions and harnesses, with live session status. Stdlib Python.
DSH host plugin: two circuit breakers — abort a runaway reasoning (thinking) loop and force a fresh no-think retry, and stop/steer repeated tool failures before they are re-run.
⚡ High-Performance LLM Gateway in Go + Rust SIMD (< 5MB RAM) • Multi-Account Pooling • 338+ Providers • Autonomous Cascades