Blazing fast, capacity-aware routing for local AI. One OpenAI-compatible endpoint for your inference servers. Built in Rust. No BS.

Shared AI agents for teams: one agent per channel, with memory, connected apps and approvals. Open source and self-hostable. Hosted at teamski.in

Always-on personal AI agents (OpenClaw, Hermes Agent, Letta, and more), memory layers, runtimes, and messaging bridges.

The Click & Install Agentic MCP Client for Home Assistant.

Claude Code skill: describe the data you want from any website and get a CSV — no selectors, no code. 스크래핑을 몰라도 'URL + 한 문장'으로 데이터를 CSV로 받는 Claude Code 스킬. Playwright analysis, sample-row confirmation, rate-limited collection, saved recipes; honest about bot checks, logins and robots.txt.

Weekly tracker of LLM rankings from the official LMArena dataset: CSV history, auto-generated trend charts (frontier race, open-weight vs proprietary), updated by GitHub Actions.

DeepSeek Harness 的 QQ 渠道插件（OneBot v11 / SnowLuma）：工具面、长期记忆、知识库、主动行为与管理后台

Daily AI news, fact-checked and traced back to its roots. A source-checked history of AI since 1943, a glossary with lineage, and the labs and people behind it. Open data, built nightly on free Gemini and Groq tiers.

Edico — AI-assisted LaTeX editor for scientific papers. Chat with Dico to refine style, structure and citations, review every edit as a diff, then compile to PDF. FastAPI · LangGraph · React 19 · PostgreSQL.

Stop re-explaining yourself to your AI. BossAlign turns corrections into scoped, human-confirmed rules — and measures whether applying them was actually right.

100% free AI chatbot on Cloudflare — no API key, no credit card

KI-Interface für Shopware, Shopify, Magento & OpenMage: Produkte, Preise, SEO und Landingpages per Chat. Die KI liest nur, geschrieben wird nach Freigabe.

An open-source desktop workspace for AI teammates, models, tools, and reviewable actions.

一只只读监控 LLM 余额与 Token 用量的蓝色鲸鱼桌面挂件，不调用模型，不产生额外 Token。

A highly scalable and pluggable evaluations repository that works with all environments to provide an unified experience for all your evaluation tasks

DSH 模型整理（模型列表整理）：隐藏用不到的模型、给模型和渠道改备注名、用箭头调整排序，保留厂商计费倍率。Model list tidy for DeepSeek Harness.

Demo code for Boole-1.7B

Agentic AI summarizer that compresses source code and technical theory into meaningful summaries. Focus keywords, source tracing, flashcards, multi-format export. Runs in your browser. Designed and Developed by NIKHIL CHARY SRIRAMOJU.

用于跨 AI Agent 会话接力的 Agent Skills，在 Claude Code、Codex、omp、pi 等任意 Agent 间实现任务无缝接力。 | Agent Skills for cross-AI-agent session handoff enable seamless task handoff between any agents, including Claude Code, Codex, omp, and pi.

AI assistant for GLPI 10, 11 and 12: reads the whole ticket (text, images, documents), drafts replies, rewrites texts and learns the classification from solved tickets. OpenAI, Azure, Anthropic, Gemini, Mistral, Ollama or any OpenAI-compatible API.

Automated football analytics: Airflow pipeline, 18-panel tactical dashboards, PostgreSQL warehouse and an AI analyst that cannot invent a statistic.

🔌 精选 AI API 中转站 / 聚合网关 / 导航比价站合集 —— 一个 Key 打通 GPT、Claude、Gemini、DeepSeek 与国产大模型

Offline AI meeting notes and transcription for Linux and macOS. Open-source Google AI Edge Foresight and Granola alternative with local Gemma LLM, Whisper, RAG and MCP.

A SillyTavern extension for scene summaries, dated archives, character memories, recaps, diaries, and continuity tracking.

Local AI router. One OpenAI-compatible endpoint for every provider you already have, and one key for opencode, claude code, Cursor and any coding agent. Keys stay on your machine.

Per-agent primary/secondary/tertiary model routing for OpenCode v2 — model fallback chains with a local web UI. Works with oh-my-opencode-slim; zero dependencies.

裸K/价格行为分析机器人：拉 Binance K线 → LLM 按固定框架判读 → OpenClaw 定时推送简报到 QQ 群。 | Naked-K / price-action analyst bot: Binance K-lines to LLM price-action briefing, pushed to a chat group via OpenClaw cron.

[EMNLP Findings 2026] HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

🔐 LLM harness that triages incoming GitHub security advisories

基于 Tauri 2 + Vue 3 的轻量级大模型 API 真实性鉴别桌面客户端，支持探针指纹比对与鹈鹕测试两种模型测试方式，快速能够方便快速识别降智与掺水模型。