#llm

Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol, Fable and Kimi K3.

Deterministic workflow control CLI for LLM (Coding) agents

Turn Codex into a full-scale ACP server. Zero deps. No OpenAI API keys. Uses your existing Codex subscription.

ACP-backed Google ADK agent adapter for Go

Simple router to aggregate multiple LLM providers with optional smart routing and MCP aggretation.

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

A self-hosted authenticating inference relay that fronts agent CLIs

Fork Pi

70 agents · 194 skills · 97 commands · 22+ hooks · semantic intent routing · self-learning memory · MCP server. Claude Code, Windsurf, Cursor, Codex, Antigravity, Cline, Roo Code, Aider, Kimi, Gemini CLI. MIT.

Symfony session message store bridge for Symfony AI Chat

Drop-in open-source agent SDK. Multi-model (Anthropic, OpenAI, Gemini, Bedrock, local), streaming, MCP, sub-agents. Built on msgspec + httpx + anyio.

Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse management, semantic versioning, and productivity workflows

Go client for The Colony (thecolony.ai) — the AI agent internet. Zero dependencies.

The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

Personal investing cockpit CLI for A/HK/US stocks, funds, watchlists, PDF reports, and Lark delivery.

Опис репозиторію не опубліковано.

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.

A terminal-native AI coding agent — a fast, scriptable TUI CLI for builders.

At long last

Launch Codex CLI through codex-relay for OpenAI-compatible providers

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

Senparc 全家桶的 AI 扩展包

Local-first private AI memory layer / Digital Brain for conversations, documents, decisions, and model-agnostic knowledge.

Claude Code Skills, Agents & Plugins — UitKit

Claude Code plugin that delegates code review, adversarial design critique, and isolated implementation to Kimi Code over the Agent Client Protocol (ACP). Security-first: Kimi works in an isolated workspace and hands back a Git patch.

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

Convert AI-generated Markdown to WhatsApp, Telegram, Discord, Slack and Instagram compatible formats using an Intermediate Representation (IR) in PHP.

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.