MCP.Market

Peon Mem MCP server

by VineetV2·io.github.VineetV2/peon-mem·v1.0.9·2 stars
No reviews yet

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

2 stars65 downloads/wk

Reviews

Write one

Nobody has reviewed Peon Mem yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Peon Mem tools (16, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • build_injection

    Build a redacted context injection from project and global memory with selection explanations.

  • end_sessionwrite action

    End a Peon session and update brain files.

  • evaluate_project

    Evaluate recall, coverage, noise, and cost for a Peon project memory folder.

  • get_context

    Return project brain context from Peon memory.

  • import_global_memory

    Import global-scoped memory records from a project brain into the global memory store.

  • inspect_brain

    Return a compact summary of a project's brain: record counts by status and the prompt injection preview.

  • maybe_process_memorywrite action

    Apply Peon's automatic cost-aware processing policy and process only when the gate says to run.

  • process_memorywrite action

    Run gated Peon AI processing for a project and update structured brain files.

  • quality_report

    Inspect Peon memory quality signals: duplicates, conflicts, stale records, and promotions.

  • query_projects

    Recall relevant beliefs from OTHER Peon projects on demand. Peon memory is isolated per project by default; call this when the user explicitly asks about another project (e.g. 'what did we decide in project Y about auth?'). Omit projectPath to search every known project; pass it to target one. Set excludeProjectPath to the current project so you only get other projects' beliefs.

  • record_event

    Record a structured Peon memory event such as a decision or preference.

  • record_message

    Record a user, assistant, or system message into Peon memory.

  • remember_global

    Upsert a global Peon memory record for cross-project reuse.

  • search_global_memory

    Search cross-project global Peon memory.

  • search_memory

    Search structured Peon memory; returns a compact ranked list with one-line reasons.

  • start_session

    Start a Peon memory session for a project.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan66 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 30 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Peon Mem compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 4,460 AI and agents servers
Tools
16
the typical AI and agents server has 6
Tools that change things
19%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 65% of 2,711 AI and agents servers
Downloads a week
65
more than 52% of 1,538 AI and agents servers with a package

What its tools let an agent do: 10 read · 1 create · 3 change · 2 run or deploy

Install Peon Mem in Claude Code, Cursor or VS Code

Runs npx -y peon-mem on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add peon-mem -- npx -y peon-mem
Add to Cursor

What the publisher says

From the Peon Mem repository's README, as published. We do not edit it. Read it on GitHub

🧠 Peon — a memory brain for your AI coding agents

Local-first, hierarchical, self-improving memory for Claude Code, Codex, and any MCP client.

Your AI forgets everything between sessions. Peon doesn't. It records your sessions, uses an LLM to consolidate them into typed beliefs, and injects the relevant ones back into every prompt. It runs as a daemon on your machine, and nothing leaves it.

PEON GLOBAL BRAIN            ← user-level facts & preferences, inherited everywhere
       /        |         \
  project A  project B  project C    ← rooted child brains (.peon/ in each project)

Why Peon

tools. Each project gets an isolated child brain. Every injection carries both.

  • Hierarchical brains. One global parent brain holds who you are, your rules, and your

facts, artifacts) give you the gist. An episodic verbatim layer recovers the exact details that lossy summaries drop. In my own LongMemEval run, raw-episodic recall scored 61% where belief-only scored 17% — self-measured, not an independent benchmark; reproduce it with npm run eval.

  • Two memory layers, honestly measured. Consolidated beliefs (decisions, preferences,

inject a query-ranked memory block (with an ⚠ MOST RELEVANT headline) into every prompt. You never have to remember to save anything.

  • Automatic capture and injection. Claude Code hooks record messages and events, then

memory accumulates. It can supersede, merge, and flag conflicts. Nothing is destructively deleted.

  • Cost-gated consolidation. An LLM distills sessions into beliefs only once enough new

recency. Query embeddings are cached to disk, so repeat prompts cost nothing.

  • Hybrid retrieval. Lexical and semantic RRF fusion, MMR diversity, reinforcement, and

a star. Projects are galaxies, search makes matches flare, and autonomous curation pulses.

  • The Neural Universe. A live monitor at localhost:3737/monitor renders every belief as

injected, what failed, what consolidation did. Then it files a report with a verdict.

  • A daily self-audit (STL). Peon checks itself every day: what it recorded, what it

fingerprint per row) means retrieval changes are proven, not asserted. Negative results stay documented.

  • Eval-gated development. A committed results ledger (git SHA, qrels, and brain

DNS-rebinding protection, secret redaction at the injection boundary, and path-traversal guards.

  • Local-first and locked down. Plain JSONL you can read, a loopback-only daemon with

The live monitor: 18k real beliefs rendered as stars. Type to make matching beliefs flare; click one to inspect it.

Ask the field: typing "wulver cluster" makes 400+ matching beliefs flare while the rest dim, and the camera flies to them.

Why "Peon"?

The name comes from Indian offices. Every office had a peon, the person who walked desk to desk all day: collect a file from this table, note who needs what, carry it to the next table, remember where everything is. He wasn't the boss or the star, but the whole office quietly ran on him. Nothing moved without him, and he never forgot where anything was.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Peon Mem: common questions

Is Peon Mem MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Peon Mem safety report
How do I install Peon Mem?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Peon Mem need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Peon Mem maintained?
The last commit was 50 days ago (2026-09-15). The latest release is v1.0.9.
What can I use instead of Peon Mem?
Servers from other publishers that do the same job: Basic Memory MCP server, Agent Recall MCP server and Total Agent Memory MCP server.
How does Peon Mem compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 16 (the typical AI and agents server has 6); tools that change things 19% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Peon Mem

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Emulo
    Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.
    A
  • Serena MCP: the IDE for your agent
    A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
    C