#llm

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

Fast CLI for Claude Code and OpenAI Codex token/cost usage analytics

Unofficial Go SDK for E2B cloud sandboxes — create, manage, and run commands in secure microVMs.

Node.js binding of llama.cpp

该仓库未发布描述。

A universal git-native AI agent framework. Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files.

Python foundation for LLM apps whose prompts and spend you can actually see — versioned prompts, every call recorded and replayable, budgets, evals, jobs.

Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.

Automated parallel code reviewer using AI Coding Agent CLIs

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

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).

After the spec: ship and run. A delivery framework for agentic systems — floor first, evolution on evidence, governance from day zero, handover with proof.

Anthropic (Claude) platform bridge for Symfony AI

PHP library for building chats with agents.

AI development assistant MCP server for Symfony projects

Official specification for Token-Oriented Object Notation (TOON)

Asset-Aware MCP Server — AI Agent precisely accesses tables, figures, sections from PDFs + .docx round-trip editing (DFM) with 46 tools / 13 resources, segmentation export, layout overlay, OCR preprocessing, knowledge graph (LightRAG)

MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

Expose djangorestframework-services services and selectors as a Model Context Protocol (MCP) 2025-11-25 Streamable HTTP server.

High performance, real-time markdown renderer for AI/LLM

Spec-first Rust port of TOON (a token-efficient data format): deterministic JSON<->TOON conversion with strict validation and streaming support

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.

The open source post-building layer for agents.

A Javascript SDK for the Linkup API

🚀 AI-powered code review tool for GitHub, GitLab, Bitbucket Cloud, Bitbucket Server, Azure DevOps and Gitea — built with LLMs like OpenAI, Claude, Gemini, Ollama, Bedrock, OpenRouter and Azure OpenAI

🧠💻 Reimagine the Internet as Self-Organizing Mind Map 🤖🔎 STREAM: Search with Top Result Extraction & Answer Model 📈📝 REASON Docs Writing Agent 🚜📜 Tractor the Text Extractor 🔤📊 SEEKTOPIC

Runtime Firewall for AI agents which catches the rogue tool call before it runs. Dangerous commands, secret leaks, prompt injection. For Claude Code, Codex and framework SDKs

Search engine

TradingAgents: Multi-Agents LLM Financial Trading Framework