Skip to content

syncable-dev/memfleet-public

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MemFleet

MemFleet

Structural intent coordination for agent fleets.
Typed intent, precomputed blast radius, O(1) coordination reads — no prose, no timing windows.

npm version license docs

Early Access — Phase 1 (intent registry, episode store, NodeState rollup, Class A/B/C, Y-doc, stdio MCP) is stable. Phase 2 (leases, shadow overlays, intent-aware auto-merge) and Phase 3 (in-process Memtrace, Ed25519 signing, CEL policy) are in flight. Report issues here.


The problem

Ten coding agents editing the same repo. The naive options:

  • Prose rationale — each agent writes a paragraph. Others read it. 200+ tokens per edit, does not scale, vendor-specific, resists structural querying.
  • Timing-based notification — broadcast in a 500 ms window, others subscribe. Works for two agents, floods at ten, breaks on network jitter.

Both produce the same outcome: silent collisions, overwrites, wasted tokens re-reading work that could have been predicted.

The solution

MemFleet treats intent as a structural type, not a paragraph. Every edit emits a typed IntentKind enum with a precomputed impact set, attached to the graph nodes it touches. Any agent reading those nodes receives the coordination picture — O(1), no prose, no timing window.

npm install -g memfleet     # binary + 10 skills + MCP server — one command
memfleet                    # MCP server auto-launched by Claude / Cursor on connect

Claude Code, Claude Desktop, and Cursor (v2.4+) pick up the skills and MCP tools automatically.

Typed intent — the core contribution

9 variants, 41 leaf values:

pub enum IntentKind {
    Refactor    { pattern: RefactorPattern },
    FeatureAdd  { surface: FeatureSurface },
    BugFix      { defect: DefectClass },
    Cleanup     { kind: CleanupKind },
    Performance { axis: PerfAxis },
    SecurityFix { severity: Severity, cve: Option<String> },
    TestAdd     { covers: Vec<NodeIdentity> },
    DocsOnly,
    Exploratory,
}

One intent ≈ 20 tokens. One prose rationale ≈ 200+. Across a 10-agent fleet running 100 edits — ~90,000 tokens saved per fleet-turn.

Conflict classes

Class Meaning Broker action
A Additive only — new symbols, no removals Auto-accepted. Zero coordination cost.
B Modification to an existing symbol — body / type / rename LWW by reference_time. Loser receives a typed ReplanHint.
C Removes a live symbol or changes a signature with active callers Blocked at intent time. Structured conflict report.

Refactor(RenameSymbol) + BugFix(NullHandling) on the same symbol are orthogonal — the broker auto-merges (Phase 2).

8 MCP Tools

Tool Purpose
publish_intent Register structural intent before an edit; returns blast radius and active conflicts
record_episode Record a structural episode after an edit; classifies A/B/C, precomputes impact, updates rollups
get_node_state O(1) read of recent episodes, active intents, dominant intent, conflict density for a symbol
get_episode Fetch a single episode by id
query_episodes Filtered episode search by node / intent / time range
ydoc_read Read the Y-doc thread + NodeState blob for a symbol
subscribe Register a streaming subscription with filters and budget
fleet_status Active intents, open subscriptions, episode count, conflict counts by class

10 Agent Skills

Skill You say...
Intent memfleet-publish-intent "I'm about to refactor X"
Episode memfleet-record-episode "I just edited X"
Node state memfleet-node-state "is anyone working on X"
Query memfleet-query-episodes "what changed today"
Subscribe memfleet-subscribe "watch the auth module"
Status memfleet-fleet-status "how busy is the fleet"

Plus 4 workflow skills that chain multiple tools:

Skill You say...
memfleet-first Meta-router — the first skill to reach for in any multi-agent edit
memfleet-safe-edit "implement/rename/modify X safely" — full publish → edit → record loop
memfleet-conflict-resolution "I hit a B/C conflict — what now"
memfleet-fleet-coordination "coordinate agents on this multi-symbol refactor"

Architecture

Agent (Claude Code / Cursor / CI bot)
        │  MCP (stdio or SSE)
        ▼
memfleet-mcp          ← single MCP endpoint agents see
        │
        ▼
broker crate          ← intent registry, episode store, CRDT classifier,
        │               rollup cache, subscription router, Y-doc, provenance log
        ▼
MemtraceBackend trait ← Phase 1: over-MCP client to a running memtrace-mcp
                        Phase 3: in-process trait swap, zero other code changes

MemFleet is composition, not replacement: it uses Memtrace for structural blast radius today and will embed it in-process in Phase 3.

Compatibility

Editor / Agent MCP Tools Skills Install
Claude Code npm install -g memfleet — fully automatic
Claude Desktop Automatic — shared with Claude Code
Cursor (v2.4+) npm install -g memfleet — fully automatic
Windsurf Coming soon Add MCP server manually
VS Code (Copilot) Add MCP server manually
Any MCP client Add MCP server manually

Setup

Claude Code + Claude Desktop

npm install -g memfleet handles everything automatically — binary, 10 skills, MCP server, plugin, and marketplace all register in one command.

For manual setup:

claude plugin marketplace add syncable-dev/memfleet-public
claude plugin install memfleet-skills@memfleet --scope user
claude mcp add memfleet -- memfleet mcp

Cursor

Cursor v2.4+ supports Agent Skills natively. npm install -g memfleet writes:

  • MCP server~/.cursor/mcp.json
  • 10 skills~/.cursor/skills/memfleet-*/SKILL.md

Project-local install (skills travel with the repo):

memfleet install --only cursor --local

Other Editors (Windsurf, VS Code, Cline)

After npm install -g memfleet, add the MCP server to your editor config:

{
  "mcpServers": {
    "memfleet": {
      "command": "memfleet",
      "args": ["mcp"],
      "env": { "RUST_LOG": "info" }
    }
  }
}

Uninstall

memfleet uninstall
npm uninstall -g memfleet

Requirements

Dependency Purpose
Node.js ≥ 18 npm installation
Rust (toolchain) Only if building from source — binaries are prebuilt
Memtrace (optional) Full structural impact — Phase-1 broker runs without it via stub

Documentation · npm · Issues

Built by Syncable · Proprietary EULA · Free to use

About

Structural intent coordination for agent fleets. Typed intent, precomputed blast radius, O(1) coordination reads — no prose, no timing windows.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors