— · Apache-2.0
Local code intelligence MCP server and CLI for AI coding agents
— · MIT
Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).
v0.91.1 · Apache-2.0
A fast object-first data engine for applications and AI agents.
— · no license
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
— · MIT
Smart code reading for humans and AI agents. Definitions, callers, dependencies and function-level diffs from tree-sitter. One binary, no index. MCP server + CLI. Install: cargo install tilth or npx tilth
— · no license
Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.
— · Apache-2.0
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
— · no license
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
v0.13.0 · Apache-2.0
Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.
— · AGPL-3.0
When you can't trust yourself with your code base, trust Arbiter.
— · MIT
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
v0.5.1 · MIT
Deterministic, persistent 3D/2D spatial world model for AI agents with entity tracking, object permanence, movement simulation, and expected view frustum projection.
— · Apache-2.0
Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust
v0.1.0 · Apache-2.0
The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.
v4.0.0 · MIT
⚡ Universal 131-Skill AI Agent Swarm Architecture for Antigravity, Claude Code, Cursor, and Windsurf. Vibe Coding 2.0 with Zero Tech Debt
v1.0.3 · MIT
OpenBitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
— · Apache-2.0
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
v0.52.0 · MIT
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
v4.4.2 · AGPL-3.0-only
MCP server that gives AI agents the web: fetch, search, crawl and screenshot from one local Rust binary. Zero API keys, zero accounts, Chrome-true TLS.
v0.0.0 · Apache-2.0
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
v0.100.0 · no license
The batteries-included, No-Code FinOps automation platform, with the AI you trust.
— · AGPL-3.0
AI-assisted PCB design for KiCAD 10. Native KiCAD plugin — a single Rust binary exposing 217 schematic, layout, routing, placement, design-review, and manufacturing tools to Claude, or the LLM of your choosing
v0.18.0 · MIT
Audit trail & traceability for AI agents — local MCP gate (Allow/Review/Deny), live receipt dashboard, trust-baseline certification.
v0.5.1 · MIT
Deterministic, persistent 3D/2D spatial world model for AI agents with entity tracking, object permanence, movement simulation, and expected view frustum projection.