The agent engineering platform.
Repository Index
47,133 repositories indexed
1–24 of 31 · Most stars
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
- claude-code
- graphrag
- knowledge-graph
- codex
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
- agent-memory
- financial-forecasting
- future-prediction
- knowledge-graph
Build resilient agents.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
- knowledge-graph
- large-language-models
- retrieval-augmented-generation
- genai
A modular graph-based Retrieval-Augmented Generation (RAG) system
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Build Real-Time Knowledge Graphs for AI Agents
Python scraper based on AI
- scraping
- scraping-python
- llm
- web-crawler
The batteries-included agent harness.
Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view
- agentneo
- agents
- ai-performance-optimization
- llm-testing
Ontology-Augmented Generation for AI agents.
- agent-skills
- document-parsing
- knowledge-graph
- mineru
Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow.
Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite.
- claude-code
- codex
- comics
- gemini
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
- ai-agents
- claude-code
- mcp
- token-optimization
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
- agent-security
- ai-agents
- audit-log
- claude-code
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
- ai-agents
- ai-scientist
- automated-research
- autoresearch
A Claude Code skill that designs a brand identity as one system: logo, typography and colour palette built together from one brief, measured, compared as identity cards, and delivered as a brand guidelines kit.
- accessibility
- agent-skills
- brand-identity
- branding
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making
11 Claude skills that port PlayStation 2 games you own to PC: reverse engineer the code, rebuild the graphics and backend, any controller, play it anywhere, then mod it however you want.
- claude
- claude-skills
- game-dev
- gamepad
⚡A curated list of awesome resources related to the Ⱥlgorand Blockchain ⛓
- awesome
- awesome-list
- algorand
- algorand-blockchain
🔍A cutting edge context aware GraphQL API fuzzing tool!
- api-testing-framework
- graphql
- api
- automated-testing
Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.