#llm

The agent framework where every run is durable, replayable, and resumable by default.

Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.

LLM Evaluation for Phoenix Apps

Self-hosted error-monitoring for Python pipelines: capture exceptions, deduplicate, diagnose root causes with LLMs, route alerts (Telegram/Slack/email/GitHub/S3), and auto-generate fix PRs — from a logging handler or one report() call.

Token-Reducing Shell — terminal output compression for AI coding agents

enola - MCP Architectural Snapshot Server and Knowledge Graph

多模型协作工作流引擎 — /ccg:go 一个命令，AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行

Collaborative application security testing between humans and agents via CLI and MCP

Model-agnostic agentic runtime for the terminal — any local model becomes a capable agent. The intelligence lives in the harness, not the weights.

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

The memory layer for AI-native development — giving AI persistent understanding of your software projects.

A pure-Go, single-file AI memory and knowledge graph library and plugin.

Опис репозиторію не опубліковано.

Automated parallel code reviewer using AI Coding Agent CLIs

An open-source terminal coding agent runtime and CLI for real project work.

Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).

Anthropic (Claude) platform bridge for Symfony AI

PHP library for building chats with agents.

AI development assistant MCP server for Symfony projects

Open-source, self-hosted AI app builder — an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.

Universal LLM API client — 163 providers, 14 native language bindings, powered by a Rust core

Coding Agent Harness

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.

Multi-agent orchestration plugin for OpenCode. 10 configurable model slots, 30 hooks, memory search, LSP diagnostics, agent-browser integration, completion controller, auto dream/distill memory consolidation. One prompt to set up and run.

TradingAgents: Multi-Agents LLM Financial Trading Framework

A type-safe abstraction layer over LLM provider SDKs for TypeScript

Shared infrastructure for go-* MCP servers: env, llm, cache, retry, metrics, strutil

Local-first AI workflows for engineers.