180 packages found
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Age
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot C
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
Exploring Zep & Knowledge Graphs with Open-Source models as an alternative to OpenAI's Assistant Threads
A repo lists papers related to LLM based agent
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous wor
Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,928-node LLM-wiki graph, 91,464 skills,
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map w
AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent dec
ICML 2026 · Plug-and-play long-term memory for LLM agents
An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language a
AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating
Fast Obsidian-aware search and discovery that makes AI agents or OpenClaw your true knowledge assistant.
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with
Open-source multi-agent platform that structures software engineering as a coordinated team of specialized AI agents. It
Build knowledge graphs from biomedical literature and query them with an LLM agent
MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
A Python-based framework for building multi-agent systems with LLMs. Currently in pre-launch alpha.
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, epi
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
A structural X-ray for the codebases AI agents are writing.
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enfo
Manage and orchestrate AI coding agents (Claude Code, Copilot, Goose, etc.) on remote machines — task decomposition, mul
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agen
MCP server for persistent context management in AI coding assistants
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a lib
Session-Driven Development - Maintain perfect context across AI coding sessions with Claude Code
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
LLM-agnostic tabletop RPG Game Master framework. Runs on OpenCode, LM Studio, or any LLM service. D&D 5e included as ref
Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapsh
SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language pr
A custom TypeScript MCP Server intended to be used with Claude Code
Multi-agent orchestration for building production apps with Claude Code. 15 agents, 12-phase pipeline, from requirements
Integrating AI into every workflow with our open-source, no-code platform, powered by the actor model for dynamic, graph
An open-source, graph-based workflow engine for Gemini/OpenCode/Claude Code/Qwen CLI. Automate ML experiments and scient
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own p
🤖 Claude Code定制化研发流程系统 - 基于Spec-Driven和Test-Driven的AI智能体团队协作框架。构建AI优先的软件开发新范式，让AI智能体团队替代传统人类开发团队。
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deplo
Never stop coding. Free AI gateway: one endpoint, 160+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline &
A memory system for Cline that tracks progress between conversations.
Multi-agent sprint orchestration for Claude Code — /tickets plans, /sprint executes
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
A Systematic Survey of Deep Research
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memor
A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18