#ai-agents

Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed knowledge graph, MCP server + CLI. No cloud, no keys.

Production-grade resilience for Go services calling LLMs and tools. Composable patterns — circuit breaker, retry, rate limit, timeout, bulkhead, fallback, hedge, adaptive concurrency, cost budget, stream timeout — with first-class OpenTelemetry, Prometheus, and slog observability. Zero core deps.

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

Local MCP server for delegating asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.

🚀 Django-CFG: Type-Safe Django Configuration Framework with AI-Ready Infrastructure

Configurable tool bundle for AI coding agents — use via MCP server, CLI, or agent skills. npm wrapper for the Rust binary.

540 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, MCP tool-poisoning reproduction. v4.9.1

The lightest AI sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection

Official MUXI SDK for Go

Agent-native course marketplace and skill registry for executable AI-agent curricula

Local docs search: copy pages to Markdown, index with SQLite FTS5, and measure retrieval quality.

An AI assistant runtime for coding and team workflows, with DingTalk AI Cards, sub-agents, memory, and scheduled events.

The Requesty integration package for the Vercel AI SDK.

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

Agentic Experience for Golang

the governed runtime for agent skill workflows, off the leash but on the record

Content backend with typed lifecycle enforcement, MCP-native API, and zero runtime dependencies. Self-hosted. Open source.

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.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.

Autonomous AI pentesting engine, continuous offensive security across web, cloud, identity, CI/CD, IaC, databases, Active Directory, Kubernetes and IoT firmware. Agentic reasoning plus real exploit execution deliver proof-based vulnerabilities. Privacy gateway: the LLM never sees your real IPs, hosts or creds, nothing leaves your perimeter.

File-backed workflow harness for reliable Claude Code and Codex sessions.

Self-improving agents, governed. Areev is the substrate for adaptive agents — agents that get better from their own history, under human authority, in steps you can inspect, undo, and re-measure.

A declarative language that compiles to professional SVG floor plans — like Typst/LaTeX, but for architecture. Built for AI agents: deterministic output, JSON diagnostics that carry their own fix, and a describe/lint channel that verifies a plan against its brief without rendering an image. Zero-dependency TypeScript.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

Launch each project's AI coding agent (Claude Code, Codex, Cursor) in its own terminal and auto-tile every window across all your monitors - DPI-correct on mixed-scale setups.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

subagent-mcp is an MCP stdio server that turns AI coding assistants (Claude Code, Codex, Gemini CLI) into managers of local Claude and Codex sub-agents on macOS, Linux, and Windows. It orchestrates locally authenticated claude and codex CLIs and can route tasks to direct API providers.

The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via MCP.