Explore

Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model chan

in the skill textuse two models at once'. Also use when upgrading model dimensions, switching providers, or A/B testing models. # What to Do When Changing Embedding Models Vectors from

Official·Skill·MIT·★ 40k in collection·No key

CLI, MCP and Skills for the world's supermarkets. Search, compare, basket and checkout across 9 providers in 6 countries — UK, Netherlands, Belgium, Spain, US, Canada. Built for AI agents.

Skill·MIT·★ 123·No key

Aiden — an autonomous AI agent and work engine built solo. It can operate your browser, terminal, files, apps, APIs, skills and tools, remember context, recover from failures, automate workflows, and

in the skill textplans, acts, recovers, and proves the result Bundled Skills · durable tools · multiple providers · connected channels · AGPL-3.0 Windows · Linux · WSL · macOS (API Mode) ``` # Aiden **Autonomous Work

Skill·AGPL-3.0·★ 853·No key

MimiClaw: Personal Agent on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS. On device Muse.

in the skill textsends the reply back. Supports both **Anthropic (Claude)** and **OpenAI (GPT)** as providers, switchable at runtime. Everything runs on a single $5 chip with all your

Skill·MIT·★ 5.8k·No key

Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration (even with classic-search term

in the skill textbrand words needed. Read its procedure before query/target questions. NOT: other KB providers, repository-file search, classic Azure AI Search index/query/app work with no Foundry

Official·Skill·MIT·★ 257 in collection·No key

Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model chan

in the skill textuse two models at once'. Also use when upgrading model dimensions, switching providers, or A/B testing models. # What to Do When Changing Embedding Models Vectors from

Official·Skill·Apache-2.0·★ 256 in collection·No key

🚀 Open-source AI coding agent for your terminal, multi-model support, tool execution, code editing, approvals, failover routing, project context, and agentic workflows.

in the skill textOnly approve changes you understand. 📚 **Full docs:** https://vritraai.vritrasec.com/ (guides, slash commands, providers, approvals, troubleshooting). --- ## 📋 Table of contents - 📸 Preview - ✨ Features - 🧠 How it works - 📦 Installation - 🚀 Usage - 🧰 Agent

Skill·MIT·★ 12·No key

AI Context Kit provides a structured, instruction-based framework for context-aware AI collaboration across LLM providers. It includes authoritative specs, canonical templates, and skills workflows fo

Skill·MIT·★ 12·No key

Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification.

in the skill textverifier and still works — Laya is an accelerant, not a dependency. ``` query ──► providers ──► cross-validate ──► ┌─────────┐ ──► LLM context pack │ LAYA │ (citations only) │ SIEVE │ noise ───────────────────►└─────────┘ ──► verify_claim (dropped

Skill·MIT·★ 19·No key

Open-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.

in the skill textNeoxra hosts the rest. ## Why brand-loom - **Model-agnostic.** One interface, four providers, BYOK. Swap models with one env var. - **No coding agent required.** Plain Python

Skill·Apache-2.0·★ 25·No key

Standalone Skill and Codex Plugin for OpenAI-compatible image generation, editing, batch workflows, QA, and focused canvas editing.

in the skill textOpenAI-Compatible Images **Generate, inspect, edit, and deliver images through configured API providers or the Codex App ChatGPT route.**  ![CI ]( English | 简体中文 OpenAI

Skill·MIT·★ 55·No key

DevOps Knowledge Harness for Agents

in the skill textClaude Code, Codex, Cursor, and Gemini** local, citable competence over **31 Terraform providers** — without web search, MCPs, or model-knowledge gaps. ```bash npm i -g @vegastack/cli

Skill·MIT·★ 2·Few stars·No key

Skill/Plugin for building multimodal AI applications with Pixeltable. Tables, computed columns, embedding search, UDFs, and 30+ AI provider integrations.

in the skill textcalling agents, and video, audio, image, and document pipelines across 25+ AI providers. The agent declares the schema as `TableModel` classes in `app.py`, creates the tables

Skill·Apache-2.0·★ 6·No key

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

in the skill textone, plus Herdr unless declined with `--no-herdr`. Pass the choice with `--providers claude` or `--providers codex` so the other reads not selected instead of failed

Skill·Apache-2.0·★ 7.4k·No key

Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tu

in the skill textnamed volume; API keys seed into `auth.json` on first run (or add providers later via the UI). Mount host projects at their identical absolute paths with

Skill·MIT·★ 317·No key

Forward videos from IM to transcript, Markdown, and your knowledge base — with raw and skill-updated outputs.

in the skill textversioned `status`/`wait`/`cancel`/`retry` protocol and checkpoint-aware retries. See ASR providers for optional local faster-whisper setup, explicit model installation, and the existing cloud

Skill·MIT·★ 165·No key

Graph Engineering for Agent Skills: a specification and toolchain for dynamically discovering context and building observable, testable, and recoverable agent workflows.

in the skill textnative file specification with a reference SDK and CLI: - versioned specifications for Providers, Graphs, Actions, Resources, Runs, and tests; - a Node.js-compatible SDK for loading and

Skill·MIT·★ 16·No key

AI agent context layer for career-related tasks.

in the skill textone provider at a time: ```bash npx vitaecontext install --provider codex ``` Supported providers: | Provider | Default destination | Activation model | | --- | --- | --- | | `shared` | Portable `SKILL.md` folders | Manual reuse or packaging

Skill·MIT·★ 83·No key

Single-binary LLM agent runtime built on Elixir/OTP: chat UI, 4-tier memory, Anthropic-compatible Skills, scheduled tasks, multi-provider LLM routing, and platform bots.

in the skill textnamed sessions. | | `/manage` | everything else. LLMs, memory, skills, **groups & members**, sessions, search providers, channels, scheduled tasks, **phrases (i18n)** — each a LiveView. | ## Features - **GraphQL capability layer** — one

Skill·MIT·★ 29·No key

Production ready. AI Agent Workflow System for Claude Code

in the skill textnot statically guaranteed, so gates deter but do not block. Run `mewkit providers codex --lifecycle` to see exactly what is enforced vs advisory. > > **Full semantic parity

Skill·MIT·★ 15·No key

Token-efficient development harness for AI coding agents. Less context, better context.

in the skill texteach an on/off switch, resolved from config ↓ ordered chain, first present wins Providers who fulfils a module: an installed skill, a builtin doc, or core itself

Skill·MIT·★ 1·Few stars·No key