#llm

composable prompt building for LLMs

No repository description published.

Lighweight coding agent.

The open-source core of RagLeap — a self-hosted RAG chat engine (document ingestion, retrieval, citations) powering RagLeap's full AI business manager: Voice AI, WhatsApp/Telegram/Discord bots, database & CRM integrations, workflow automation, and a private executive assistant. Foundation layer — hosted platform at ragleap.com

⚡ The approval-first, open-source database & knowledge base for AI agents — review & approve every change before it's trusted. Local-first, self-hostable Airtable/Notion alternative.

Switch Claude Code's backend per terminal — one command, no global config.

The agentic video editor SDK — build, caption & render short-form video in code. Drive Morpha with the same tool catalog as MCP; render frames to PNG. npm: morpha-studio-sdk

OpenCode plugin provider for 9Router — FREE AI Router & Token Saver. 40+ providers, 100+ models.

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

CLI for the AISA unified AI infrastructure platform - access 70+ LLMs, web search, finance, Twitter, and video generation APIs

Python port of pi-mono: fully-aligned coding agent with TUI, ai, agent, and coding-agent packages

No repository description published.

No repository description published.

Transaction-ready context for AI agents. Like llms.txt, but for e-commerce.

Capability-driven autonomous project execution engine. Iterates an Operator loop over a goal, dispatching modular capabilities (Architect, CodeGenerator, TestRunner, BugFixer, etc.) until the project reaches a desired artifact state. No LangGraph dependency — designed as a standalone Layer 2 that antcrew (Layer 1) builds on top of.

Provider-agnostic multi-agent coding orchestrator in Go. Unified router for any LLM provider (Ollama local+cloud, OpenAI, Anthropic, Google Gemini) with role-based model assignment, fallback chains, and cost tracking. Inspired by gastown and LiteLLM.

No repository description published.

No repository description published.

Herrscher Backend plugin: the only module that talks to Claude — implements the contracts.Backend port, streaming Claude Code stream-json turns.

将 maibot 作为 docker 托管的消息回复后端运行，使用 mai.ko 桥接消息收发

No repository description published.

No repository description published.

TrikeDB — the single-file graph database. A knowledge graph in one YAML file, full SPARQL 1.1, built for LLM agents

Search electronic parts, download datasheets, and extract structured data for LLM agents — Mouser & DigiKey CLI in Rust

LLM capabilities registry and CLI tool

🧬 ModelMix - Unified API for Diverse AI Language Models.

A layered proxy to ensure almost near full compatibility with OpenAI , worry native tooling mapped like search and sandboxes

Agent-native hosting: coding agents deploy apps to a live URL in one command - no account, no CAPTCHA. CLI + MCP server, Apache-2.0.

A workspace for developing Medusa plugins and the SvelteKit storefront SDK

Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.