ai-memory — Persistent Memory for Any AI

by alphaonedev

315 downloads
Not rated
GitHub

About

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories locally in SQLite, ranks by 6-factor scoring, returns results in TOON compact format (79% smaller than JSON). 17 MCP tools, 20 HTTP endpoints, 25 CLI commands. 4 tiers from keyword to autonomous

Details

Author
alphaonedev
Downloads
315
Categories
Productivity, Other, AI, Knowledge Base, Developer Tools

- Zero token cost until memory_recall is called
- TOON format responses are 79% smaller than JSON
- Six

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name ai-memory — Persistent Memory for Any AI
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install ai-memory via cargo install ai-memory. Then use its 17 MCP tools such as memory_store, memory_recall, memory_search, and memory_list. The default tier is semantic; you can switch to keyword, smart (with Ollama), or autonomous (with Ollama) as needed.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "ai-memory \u2014 persistent memory for any ai": {
            "memory": {
                "command": "ai-memory",
                "args": [
                    "--db",
                    "~/.claude/ai-memory.db",
                    "mcp",
                    "--tier",
                    "semantic"
                ]
            }
        }
    }
}

McpServers

{
    "memory": {
        "command": "ai-memory",
        "args": [
            "--db",
            "~/.claude/ai-memory.db",
            "mcp",
            "--tier",
            "semantic"
        ]
    }
}

Distributed coordination substrate (Pillar-1,](https://github.com/alphaonedev/ai-memory-mcp/blob/HEAD/docs/v0.8.0/release-notes.md)#1709)

- Actions — the dependency DAG(schema v59). Typed action nodes with a state machine (pending → claimed → in_progress → done/failed/abandoned), typed DAG edges (requires/unlocks/blocks/gated_by/sibling), and frontier/next surfaces that pull the next runnable node. 8 MCP tools (memory_action_create/_get/_transition/_list/_add_edge/_edges/_frontier/_next).
- Leases — single-holder, TTL-bounded claims(schema v59). Heartbeat-renewed compare-and-swap claim (PRIMARY KEYonaction_id= one holder at a time) plus an hourly lease-sweeper. 4 MCP tools (memory_lease_acquire/_renew/_release/_get).
- Signals — typed, Ed25519-signed inter-agent messages(schema v60). Each carries a signature + sendersigner_pubkeyand threads viacorrelation_id/in_reply_to. 5 MCP tools (memory_signal_send/_read/_inbox/_thread/_ack).
- Checkpoints — attested conditional gates(schema v61). A gate that blocks until a condition resolves; resolution is self-signed in place (Ed25519) for separation-of-duties, andverifyre-checks the signature. 4 MCP tools (memory_checkpoint_create/_resolve/_query/_verify).
- Routines — parameterised, frozen, replayable plans(schema v62). Authored as adraft, thenfrozen(immutable, Ed25519 freeze-attestation);runmaterialises a concrete set of actions + edges from a{{param}}template into aroutine_runsrecord. 5 MCP tools (memory_routine_create/_freeze/_run/_status/_list).
- Every coordination state-mutation appends a tamper-evidentcoordination.<op>row to thesigned_eventsV-4 hash chain (
#1722); the two authority-granting writes are mirrored onto the HTTP daemon (POST /api/v1/actions/{id}/transition,POST /api/v1/signals) with local CAS + W-of-N federation fan-out (#1718).

Thememory_kindvocabulary extends withgoal/plan/step; the closedmemory_links.relationtaxonomy extends6 → 9 relations(decomposes_into/depends_on/advances, schema v63); and a first-classmemories.lifecycle_statecolumn (schema v64) makes Goal/Plan/Step a real state machine (open → active → blocked/done/abandoned), enforced across the MCP / HTTP / SAL surfaces with an illegal edge mapping to HTTP409 CONFLICT. TheMemorystruct grows to27 fields. No new MCP tool — the v64 work adds only permissive optional request fields.

Peer enrollment ON by default (#1789), per-transition signatures on authority-granting writes (#1718), per-write content attestation for relayed memories (#1464), transition-replay nonces (#1805), and outbound peer-cert fingerprint pinning (#1678). Heterogeneous fleets that don't have to trust each other —review the secure-default flipsin[docs/v0.8.0/release-notes.md§"Federation hardening" before upgrading.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.