Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

See how you really use AI — X-ray your AI coding sessions locally

Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools.

Publishes localhost services to the agentic web through self-hostable, trustless relays.

Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Agent skills for administering a real UniFi network over its local API: auth, zone firewall, Wi-Fi, clients, and the site map.

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structural awareness: call graphs, impact analysis, symbol search, and more.

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Drive x64dbg with your AI. MCP server: 23 mega-tools / 153 endpoints for breakpoints, memory, disasm, tracing, anti-debug & PE dumping. Claude/Cursor/Windsurf/Cline. All local.

Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — cross-platform desktop app powered by Spring AI.

A ruleset that turns AI coding assistants (e.g. Claude Code) into disciplined Linux, FreeBSD & macOS sysadmins. Manages servers via SSH and localhost with safety guardrails, checklists, and team support. Named after the Heinzelmännchen — helpful kobolds who do the housework while you sleep.

Security testing that runs inside the coding agent you already use. Source-available, not open source.