Skip to main content
Glama

What one agent learns in a session, every agent knows in the next.

How it works

  1. Tell one agent once: a decision, a root cause, a correction.

  2. Renor saves it as plain Markdown you own.

  3. Every agent recalls it in its next session: Claude Code, Codex, Cursor, Grok, Gemini, VS Code, OpenCode, Pi or any MCP client.

Related MCP server: agtmem-mcp

Quickstart

Two ways in. Both take under a minute.

Hosted: the easiest path

npx renor connect --client claude-code

--client is claude-code, codex, cursor, grok, gemini, vscode, opencode or pi. One command adds Renor to that app, signs you in through the app's own flow (no token to copy), writes the memory rule below, and ends with a live check that your workspace answers. Search is hybrid (keywords and meaning). Sign up at renor.cloud.

Self-hosted: the private path

Your memory stays in a folder on your machine. No account, no API key. You need Node.js 22.16 or later (22.16+ or 24+); on an older Node, renor-engine prints one line saying so and exits.

claude mcp add --scope user renor-local -- npx -y renor-engine mcp
codex mcp add renor-local -- npx -y renor-engine mcp

Restart the agent. The first start downloads about 12 MB, and the first Renor call works about 3 seconds after an empty start. Notes go to ~/.renor (set VAULT_PATH to use another folder).

Updates. The command above updates itself: npx -y renor-engine mcp fetches the newest release each time the app starts, so there is nothing to upgrade by hand. It needs the npm registry at that moment; with the registry unreachable (offline, blocked, an outage) it does not start, even with a copy on the disk. To see what you have, run npx -y renor-engine status (the installed version and, when the registry answers within 2 seconds, the latest; nothing is asked when sharing is off or DO_NOT_TRACK=1). To pin a version, write it in the command: npx -y renor-engine@1.4.10 mcp. A machine that must start offline can use npx --prefer-offline -y renor-engine mcp, which prefers the cached copy; it was measured by scripts/npx/measure-npx-update.sh, and what it costs (it may keep an older copy when the registry is reachable) is in that script's table.

Then add the memory rule to the agent's instructions file, so it saves on its own.

Cursor or VS Code, one click:

Add to Cursor Add to VS Code

Grok. Grok starts project servers only in a folder it trusts, so register Renor in the project:

grok mcp add --scope project renor -- npx -y renor-engine mcp

Trust the folder in Grok, then restart Grok. To check it: ask Grok to save a real decision from your project, restart Grok, and ask about it in the new session. To turn telemetry off, set DO_NOT_TRACK=1 in the environment Grok runs in. Paste the memory rule into the project's AGENTS.md.

Any other MCP client: the command is npx with the arguments -y renor-engine mcp (stdio).

Check it works:

npx renor-engine status

Something wrong? npx renor-engine doctor is a read-only health report (folder, index, ledger, embeddings, client configs) that is safe to paste into a support request; secrets are redacted. See troubleshooting.

Then tell your agent a real decision ("remember that the orders service uses Postgres 16"), start a new session, and ask about it.

Running it on a server or with Docker: docs/self-hosting.md.

Several agents on one memory: start each with its own RENOR_CONNECTION_NAME and they get the multi-agent ("hive") tools (details).

The memory rule

Five lines that make agents save decisions, corrections and facts on their own. In our Grok test (grok-4.7, renor-engine 1.4.0, 3 Nov 2026), agents with the rule saved in 8 of 8 sessions and the next session recalled 5 of 5 project facts.

renor connect writes it for you. Self-hosted, paste it into ~/.claude/CLAUDE.md (Claude Code), ~/.codex/AGENTS.md (Codex) or the project's AGENTS.md (Grok):

## Renor memory

Renor is connected to this app and remembers across sessions.
- Before deciding anything non-trivial, recall first: one get_context call is usually enough.
- Save with remember when the user makes a decision, corrects you, or states a fact that should outlive this chat. Include the reason.
- Save the specific value (a port, a name, a path), not a summary of it.
- Do not save secrets, or things that are already in the code.

Self-hosted, renor-engine mcp lists the same names as the hosted service: whats_new, get_context, search_text, retrieve_memory and remember (tool list). The older names (search, remember_fact, note) are behind RENOR_MCP_LEGACY_STDIO=1.

What runs on your machine

  • Your memory is plain Markdown in one folder you own. Edit it with anything; back it up like any folder.

  • SQLite holds the search index, next to the notes. It is rebuilt from the Markdown at any time.

  • No embedding model needed. Search is by keyword; when the exact words miss, it retries with word stems. Hybrid search (keywords and meaning) is the hosted default; self-hosters can opt in to OpenAI or a local model (details).

  • Small: a 1.8 MB package, about 5 MB installed. About 143 MB of memory with 1,000 saved memories.

  • Telemetry: anonymous usage numbers (never text, names or paths) are on by default, with a notice on first run. renor-engine telemetry off or DO_NOT_TRACK=1 turns them off. Your memory text is never shared unless you say yes to that separately. Every field: docs/TELEMETRY.md.

Benchmarks

Benchmark

Renor

Setup

LongMemEval-S

98.4% (492/500)

Default (deep search)

LongMemEval-S

94.4% (472/500)

Lean mode (RENOR_DEEP_SEARCH=0)

LoCoMo (categories 1 to 4)

96.7% (1,489/1,540)

Default (deep search)

BEAM 128K / 1M / 10M

76.2 / 74.7 / 60.2

Default (deep search), score out of 100

Claude Opus 5.5 answers LongMemEval, LoCoMo and BEAM. One run each, Oct 2026. Deep search, the default, reads 50 matches with a 4,000-token budget; get_context replies in up to 8,000 tokens. Lean mode (RENOR_DEEP_SEARCH=0) reads 20 matches with 1,300 tokens and an 800-token get_context. These runs used Vertex embeddings, as hosted Renor does; without an embedding model, self-hosted search is by keyword only, which they do not measure. Judges and methods for every run: renor.cloud/research.

Build from source

You need Node.js 22.16 or later and git.

git clone https://github.com/renorai/renor-engine.git
cd renor-engine
npm ci && npm run build
node scripts/smoke-self-hosted.mjs

The last command starts the MCP server in a temporary folder, saves one fact, finds it again and ends with PASS: self-hosted stdio MCP can remember and retrieve a current fact. It never touches your notes. Downloaded a ZIP instead of cloning? Build with RENOR_BUILD_COMMIT=0000000 npm run build. Connecting a local build to each agent: docs/self-hosting.md.

Learn more

Docs · Self-hosting, servers and Docker · Every setting · Telemetry

License and contributing

The engine is Apache-2.0 (LICENSE); 1.0.0 was released under AGPL-3.0; 1.1.0 and later are Apache-2.0; files imported from the upstream project stay ISC (NOTICE, UPSTREAM.md). The renor CLI, the SDKs and the integrations are MIT.

Contributions are welcome: CONTRIBUTING.md has setup, tests and good first issues. Sign off each commit with the DCO (git commit -s); there is no CLA. Report vulnerabilities privately as described in SECURITY.md.

If Renor saves you re-explaining, a ⭐ helps other developers find it.

Available Tools

8 tools
entityBInspect

Look up an entity (person, project, concept) by name or alias. Returns entity details or null.

Inputs: name (required).

evidenceAInspect

Question-conditioned evidence extraction. Retrieves like search and then lists every distinct item/event/amount relevant to the question, with dates. Best for how-many / how-much / count / list / aggregate questions about the user's history. It never computes totals — count or sum the items yourself and prefer items with dates matching the question window. Identical questions over unchanged history replay from a content-addressed cache at zero model cost. Gated by RENOR_EVIDENCE_MODE (off | auto | always); call with force: true to run even when auto declines.

Inputs: query (required), topK, force.

factsAInspect

All current lifecycle facts for an entity (name / entityName / subject; aliases). Prefer search for a natural-language question. asOf / includeHistory for temporal reads.

Inputs: asOf, name, entityName, includeHistory.

keywordAInspect

Exact keyword/BM25 search only: the query is matched as one exact phrase, and OR, AND, NEAR and * are plain words, not operators. Use search for identity and natural-language questions. Hyphens are quoted server-side. When the term appears in no chunk text, it is matched against note paths and frontmatter too, so a task id, slug or file name finds the note that carries it (reason: "note-identity").

Inputs: query (required), topK.

noteBInspect

Store a memory entry in the daily notes. Appends text to the daily note for the given date.

Inputs: text (required), date, source. Returns: ok, path, detail, warning

remember_factAInspect

Durable memory write: stores (or supersedes) a fact about a subject. Ledger-first (survives index rebuild), temporal (closes the previous current fact for that subject+predicate). Returns a receipt. Use for "remember that…" statements. Confidence is not representable in the ledger.

Inputs: object (required), subject (required), predicate (required), source. Returns: action

statusAInspect

Get vault index statistics: count of notes, chunks, entities, facts, and relations.

Inputs: no named parameters. Returns: facts, notes, chunks, entities, +1 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 8 tools

    Disambiguation4/5

    The retrieval tools (search, keyword, evidence, facts, entity) overlap in input space, but the descriptions draw useful boundaries: default semantic search, exact BM25, question-conditioned aggregation, lifecycle facts, and entity lookup. Selection guidance is clear enough to avoid most misselection, though entity vs facts remains slightly fuzzy.

    Naming Consistency3/5

    The tool names mix bare nouns (entity, facts, status, note, evidence, keyword, search) with one verb_noun form (remember_fact). There is no case or separator chaos, but also no predictable pattern. Readable, yet inconsistent.

    Tool Count5/5

    Eight tools is well within the appropriate range for a memory/search server, and each maps to a distinct capability: fact write, note append, entity/fact lookup, status, and several retrieval modes. Some retrieval variants are close, but the count itself is healthy.

    Completeness3/5

    Core memory read/write and search are present, but lifecycle coverage lacks explicit forget/delete for facts or notes, note update, and entity/relation mutation despite relations appearing in status. Agents can search and append but will hit dead ends for cleanup and relation management.

    Maintenance

    ActivityActive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Provides cross-session persistent memory for coding agents via MCP tools to store, retrieve, and manage notes with hybrid keyword/semantic search and automatic deduplication.
      8
      237 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables coding agents to store, search, and retrieve long-term memory as plain Markdown files with a disposable SQLite index, including note management, decision/bug tracking, and codebase symbol lookup via MCP.
      8
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides coding agents with persistent local memory by exposing tools to save, search, and retrieve decisions, bugs, and context as Markdown with hybrid keyword and semantic search.
      4
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Gives coding agents a persistent memory by searching a local, read-only index of existing markdown and letting them write findings back as notes that the next session can retrieve. It serves ranked, context-sized results over MCP, injects standing conventions at session start, and keeps data on your machine with secret redaction and archive-only deletion.
      111 PyPI
      MIT