memory_compress

4 registry entries were observed exposing a tool named memory_compress — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,342 of 40,590 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. fleet-memory-mcpMCPattestedtrust 85/100 · A
    v0.1.0

    RCLL — self-hosted, hierarchical shared memory for a team of AI agents over MCP (rooms, L0-L3 depth, pgvector). Fork of vectorize-io/hindsight.

    ClaudeCursorCopilotGemini
    UnknownMIT1mo agonpmGitHubobserved · static extraction
    mcpmemoryrcllfleet-memoryhindsightai-agents
  2. toon-memoryMCPattestedtrust 85/100 · A
    v4.3.5

    Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

    ClaudeCursorCopilotGemini
    io.github.LuiggiVal08Unknown2mo agonpmGitHubobserved · static extraction
    mcp
  3. io.github.NaNMesh/nan-forgetMCPcommunitytrust 60/100 · B
    v0.6.8
    ★ 5

    AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.

    ClaudeCursorCopilotGemini
    io.github.NaNMeshUnknown6mo agonpmGitHubobserved · static extraction
    mcp
  4. hindsight-mempalace-mcpMCPcommunitytrust 60/100 · B
    v1.0.0

    Standalone MCP server for Hindsight MemPalace — hierarchical AI memory with Rooms, Halls, Layers, Closets, and Tunnels

    ClaudeCursorCopilotGemini
    UnknownMIT3mo agonpmGitHubobserved · static extraction
    mcpmemoryhindsightmempalaceai-agentslong-term-memory

All indexed toolsSearch the registry for memory_compress