Lockkeeper
Local installio.github.Hannay001/lockkeeper
Routes each task to the few skills, MCP servers and tools that fit it.
4,965 servers in AI & Agents
Routes each task to the few skills, MCP servers and tools that fit it.
Ask a human before your agent acts: approval requests decided on a phone.
Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.
A second opinion from an unrelated AI model before you commit to a decision.
A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.
Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.
Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.
Shared memory for coding agents: projects, reusable code, sessions and commits across machines
AgentBadge MCP — agent-readiness scan, passport, discovery, marketplace and circle-payments tools
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.
A record of what an agent did that the agent cannot quietly rewrite, and a way for anyone to check.
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Let Codex orchestrate external coding agents through their native harnesses.
Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.
Lets an agent pay for x402 APIs in USDC on Arc, under a spending policy it cannot change.
Cross-session memory for AI coding agents via six tools; local-first SQLite store.
Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB
SkillOS MCP Runtime exposes the SkillOS skill registry as activatable MCP tools for AI agents.
MIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign.
Where the work is, packed before the agent reads: brief, symbol tables, findings, token bill.
Typed decision tools for AI agents, powered by TypeSafe Jev.
Resumable API pagination, repeated-failure detection and tool-progress cache hints for AI agents
Verify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
Cognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.
Usage & quota tracker for AI subscription accounts (StepFun, Command Code)
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Native Weavatrix MCP: 67 read-only tools for code, local CI, n8n, Dify, agents, Mermaid, Web3.
Local Mac tools plus outbound pairing for the Ganado Bridge managed relay preview.