Explore

Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.

Python·Apache-2.0·★ 100·No key

Local-first Developer Context Daemon with explicit state, memory, and policy layers.

Python·MIT·★ 2·Few stars·No key

Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.

Skill·Apache-2.0·★ 8·No key

Policy-aware MCP routing fabric for secure remote module access, capability-based orchestration, and large-context agent execution.

Go·Apache-2.0·Few stars·No key

Broker-neutral process, evidence, and control layer for financial agents: Capital Constitutions, a hash-chained decision ledger, offline-verifiable proofs, and a stdio MCP companion. Research prototyp

Skill·Apache-2.0·Few stars·No key

MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.

Python·MIT·★ 18·No key

Local-first PCB automation for KiCad with safe MCP tools and deterministic autorouting research.

Python·Apache-2.0·★ 2·Few stars·No key

Neutral trust registry for MCP servers — check before you connect

Python·MIT·Few stars·No key

Windows-first, resource-governed MCP runtime for local developer workstations with durable execution, scoped filesystem access, search, and developer-context backends.

Python·Apache-2.0·Few stars·No key

Public-domain PSP and CDL standards, reference LLM/MCP proxies, and reproducible workflow-security evaluation. Sponsored by RealflowCloud, Inc.

Skill·Apache-2.0·Few stars·No key

Kubernetes Operator for declarative AI agent lifecycle, multi-tenant quotas, metric-driven autoscaling, canary rollouts, and Model Context Protocol (MCP) discovery.

Go·Apache-2.0·★ 1·Few stars·No key

Pre-merge and pre-install trust checks for AI-agent skills and MCP configurations. Scan capabilities, detect risky changes, and block unapproved agent behavior in CI.

Python·MIT·★ 2·Few stars·No key

Zero-trust API firewall and security integrity layer for autonomous AI agents & Model Context Protocol (MCP) tool execution. Secure, TOCTOU-proof, fail-closed.

Skill·MIT·★ 1·Few stars·No key

One web page where several independent care organisations answer a person's agent at the same time, and compose one plan between them.

Skill·MIT·Few stars·No key

Diagnoses, remediates, and manages Identity and Access Management (IAM) access issues on Google Cloud. Supports two distinct operational modes: (1) Requester Flow for developers encountering access de

Official·Skill·Apache-2.0·★ 21k in collection·No key

MCP server giving LLM agents real authorization answers: evaluate Rego in-process via OPA, or ask an OpenID AuthZEN 1.0 PDP

Docker·MIT·★ 1·Few stars·No key

Public proof surface for PFC-style execution-boundary governance and signed runtime admission receipts.

Skill·MIT·Few stars·No key

Zero-trust governance layer for Claude Code. Policy-enforced MCP gateway with autonomy controls, middleware chain, audit log, HALT kill-switch, and prompt-injection defense.

Node.js·MIT·★ 1·Few stars·No key

Experimental MCP policy lab: simulate transcript decisions and verify tamper-evident audits over stdio or local Streamable HTTP.

Skill·MIT·Few stars·No key

goalert-mcp — MCP server for GoAlert: manage on-call alerts, schedules & escalation policies from Claude & other LLMs

Node.js·MIT·★ 2·Few stars·No key

An MCP server that lets AI agents operate a multi-cluster Kubernetes fleet through an Open Cluster Management hub, with policy, approval, and audit between the model and your clusters.

Python·Apache-2.0·★ 17·No key

Read-only Kubernetes and AWS access for AI agents, behind a deny-by-default policy gate with a JSONL audit trail and eval suites that score both per-call block rate and whole-trajectory behaviour.

Skill·MIT·Few stars·No key