#llm

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.

Go reimplementation of pi.ai core with multi-provider LLM streaming, a CLI, and a single-agent runtime.

Claude Code Skills, Agents & Plugins — UitKit

Unofficial MCP server for Twine

Опис репозиторію не опубліковано.

High-performance framework for building interactive workflow systems in Rust. Designed for complex workflows and multi-agent systems

Python SDK for Niadra: shared customer memory for every AI agent in a company. Context before the model call, history, tools and MCP.

GUI agent using WebMCP polyfill. Control web interfaces with natural language

Tiny Semantic Versioning (SemVer) library with LLMs and GitHub CI, that doesn't depend on 300K lines of JavaScript code and fits in a single Python file

Claude Code plugin marketplace: the bitranox skill collection (82 skills) plus a self-improve Stop hook. Skills invoke as /bitranox:<skill>.

Orchestration under Claude Code on herdr: flows an agent cannot skip, jobs on a clock, threads with claims, and a forum agents search later

Open-source TypeScript tools for production AI interfaces — agents, generative UI, chat, streaming parsers, and fast data grids.

Опис репозиторію не опубліковано.

Framework-agnostic design system for oriz.in sites — atomic @chirag127/* packages (tokens, themes, web-component atoms). One package set, a distinct look per site.

A harness for AI coding: repo-native memory, module charters, and a closed loop for navigation coding.

Serve any Streamlit app as an MCP server — agents drive it natively, no browser automation.

Web frontend for the pi coding agent: A chat UI, WebSocket bridge, password auth, and PWA support

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

Sandboxed JSON-over-stdin/stdout tool executor for AI coding agents with 19 tools, workspace confinement, and guarded mutation.

Composable pre-call and post-call hooks for LLM API calls: pricing, budgets, cost caps, rate limits, event log, observability.

Give your AI assistant secure, read-only access to your bank accounts. MCP server supporting Plaid, Teller, Enable Banking, and Tink.

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.

Semantic similarity testing for Elixir. Test LLM outputs, chatbots, and NLP in Elixir

A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.

Опис репозиторію не опубліковано.

🎭♪ Figaro, a coding agent. Pronto prontissimo.

Governed execution trees for AI agents: budget it, gate it, replay it.

load-bearing, load-bearing, load-bearing, load-bearing, load-bearing, load-bearing, load-bearing, load-bearing.

The Context Graph Protocol is an open wire protocol for context retrieval. It treats a piece of context as a typed, budgeted, provenance-carrying, consent-gated, and conformance-verified unit of exchange called a frame — never a blob.