#ai-agents

On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.

Intent-driven Agent OS for Human-in-the-loop. Fancy autonomuos delivery mode?

Keine Repository-Beschreibung veröffentlicht.

The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent traverses instead of guessing, and simulates any action to a receipt before money moves.

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

Genre-agnostic TypeScript game engine SDK — pure core plus React, Convex, WebSocket, Node host, and Postgres adapters

Workspace and context manager for domain specific AI automation and large scale AI workflows

SAGE — Save AI coding tokens by compressing terminal output, keeping raw logs local, and tracking real savings. 🧠S.A.G.E - Smart Agent Guidance Engine for AI coding assistants. by⚡ PsYc+GoD AI&ML 🤖 | IF YOU DONOT USE SAGE RUN install or PYTEST. SAGE WILL NOT ACTIVATE IN YOUR LOCAL ENVIORMENT.

Autopilot for AI Coding Agents, supports OpenCode, Claude Code, pi.dev, Cursor, and many more

Semantic + structural code search for AI-native development

Decentralized networking protocol for AI agents — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.

Automate Ghidra reverse engineering from the command line — headless analysis, decompilation, and structured JSON output for AI agents like Claude Code

Standalone DAG workflow engine for Go — 15 step types, MCP integration, durable Postgres execution (SKIP LOCKED), templates, approvals, crash recovery

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

AI-native TypeScript 3D SDK for browser 3D apps, prompt-to-code scenes, GLB/glTF product viewers, WebGL/WebGPU, Vite templates, diagnostics, and deploy checks.

A local, filesystem-backed project manager for humans and agent teams.

Give coding agents a disposable Linux VM, not your laptop

Keyless-first MCP server — 150 tools for US federal + state/local (SLED) government contracting, spending, regulation & partner vetting. SAM.gov, USAspending, Grants.gov, OFAC, FDIC, EPA, CourtListener + 45 more. No API key. Honesty-hardened.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

A tmux-native workspace for multi-agent AI development across Claude Code, Codex, and Antigravity.

Host + AG-UI bridge for LangGraph agents — agent-spec loading, layered config, and typed in-process streaming

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

Harness-agnostic toolkit for AI coding agents: detect the harness (Claude, Codex, Cursor, Cline, Gemini, Aider...) and run a pure policy core. One Bun-native package.

Keep docs and AI-agent instructions in sync. Scaffold docs-as-code, generate agent files, and fail CI when docs drift.

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Sandbox runtime for AI coding agents. Firecracker microVMs, a single Go binary, snapshot/fork as first-class primitives.

🧙 Grimoire is a free, open-source package manager for best practices — 1000+ skills across 26 domains (engineering, law, finance, design, health, and more), each sourced from a real institution or study. Install once, and your AI routes to the right skill automatically.

OpenCode Plugin for supervised agentic software development on a Kanban board

Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/