How do I install memx?

Run these in Claude Code: npx -y skills add NeoLi00/memX --agent claude-code. Then prompt normally.

Does memx auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Data

Plugin

memx

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

FLOW.md

neoli00@neoli00

GitHub

Plugin Signal62/100Solid

maintained63

capable56

documented75

adopted57

Install

$ npx -y skills add NeoLi00/memX --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript Node Bash

+4 tags

GitHub Anthropic OpenAI MCP

465

Stars

Forks

Maintained

Maintenance

TypeScript

Language

MIT

License

2mo ago

Last commit

3mo ago

Created

Repo: NeoLi00/memX

In this plugin

12 hooks 1 MCP 1 skill

MCP
- memx
skills
- memx

See everything inside

What's inside

Skills

/memxUse when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.

Hooks

SessionStartRuns on the SessionStart event.UserPromptSubmitRuns on the UserPromptSubmit event.PreToolUseRuns on the PreToolUse event.PostToolUseRuns on the PostToolUse event.PostToolUseFailureRuns on the PostToolUseFailure event.PreCompactRuns on the PreCompact event.

Show all 12 hooks

SubagentStartRuns on the SubagentStart event.SubagentStopRuns on the SubagentStop event.NotificationRuns on the Notification event.TaskCompletedRuns on the TaskCompleted event.StopRuns on the Stop event.SessionEndRuns on the SessionEnd event.

MCP

memxnode

README

Read on GitHub

memX turns completed work into structured, searchable, self-maintained memory, then injects only the evidence an agent needs for the current query. It connects natively to Codex, Claude Code, and OpenClaw, and reaches any MCP-compatible client through the same local memory layer.

Benchmarks

Architecture

Agent support

Quick start

Requirements: Node.js 22.14+ or Node 24. OpenClaw installs require OpenClaw 2026.3.25+. Python 3 is needed only for the default local embedding runtime.

The README commands use the GitHub package spec. A fresh run pulls current GitHub code, so installs do not wait for an npm publish. To use the npm release channel later, replace github:NeoLi00/memX with @neoli00/memx.

Fill in these values before running a command:

--llm-provider: the provider adapter memX should call. Choose one of openai-compatible, anthropic, google, or ollama.
--llm-base-url: the base URL for that provider. Examples: https://api.openai.com/v1, https://api.anthropic.com/v1, https://generativelanguage.googleapis.com/v1beta, or http://127.0.0.1:11434 for Ollama.
--llm-model: the model memX uses for memory compilation, recall planning, and maintenance. Pick a fast, low-cost model with reliable JSON output.
--llm-api-key: the API key for the provider. Use --llm-api-key-env PROVIDER_API_KEY if you want the config to reference an environment variable instead of storing plaintext. For local Ollama, omit the key.

The default embedding setup is local sentence-transformers-local with intfloat/multilingual-e5-small. Add --embedding-provider and --embedding-model only when you want to override that default. Use --dry-run to preview the files and exec-form commands before writing anything.

For Codex and Claude Code, native hooks are the default lifecycle path for automatic recall and turn capture. Quickstart installs the native plugin, writes the shared memX config, starts or refreshes the managed local memX service, and keeps MCP memory tools hidden with --mcp-tools none by default. This prevents duplicate recall/write and prevents the agent from reading audit data as a side channel. Use --mcp-tools full only when you intentionally want the agent to see the complete MCP tool set. Generic MCP quickstart stays full by default because it has no native lifecycle hooks. Default native memories are also host-scoped, so Codex and Claude Code do not share the same local database unless you deliberately override the database path and actor settings.

If http://127.0.0.1:3878 is already used by an unmanaged memX-compatible service, quickstart stops instead of silently reusing it. Stop the old service or pass a free local URL, for example --memx-url http://127.0.0.1:3888.

Claude Code

This installs the shared memX config, a local Claude Code plugin marketplace, native lifecycle hooks, and the managed local memX service in one run.

npx -y -p github:NeoLi00/memX memx quickstart claude-code \
  --llm-provider openai-compatible \
  --llm-base-url https://llm.example.com/v1 \
  --llm-model fast-memory-model \
  --llm-api-key sk-your-provider-key

Codex

This installs the shared memX config, a local Codex plugin marketplace, native lifecycle hooks, and the managed local memX service in one run.

npx -y -p github:NeoLi00/memX memx quickstart codex \
  --llm-provider openai-compatible \
  --llm-base-url https://llm.example.com/v1 \
  --llm-model fast-memory-model \
  --llm-api-key sk-your-provider-key

OpenClaw

npx -y -p github:NeoLi00/memX memx quickstart openclaw \
  --llm-provider openai-compatible \
  --llm-base-url https://llm.example.com/v1 \
  --llm-model fast-memory-model \
  --llm-api-key sk-your-provider-key

Generic MCP

Use this path for MCP clients that do not have a native memX lifecycle adapter. Quickstart writes the shared memX config, starts the managed local memX service, and prints a ready-to-copy MCP server config.

npx -y -p github:NeoLi00/memX memx quickstart mcp \
  --llm-provider openai-compatible \
  --llm-base-url https://llm.example.com/v1 \
  --llm-model fast-memory-model \
  --llm-api-key sk-your-provider-key

Service management

npx -y -p github:NeoLi00/memX memx service status
npx -y -p github:NeoLi00/memX memx service restart
npx -y -p github:NeoLi00/memX memx service stop

Use the same --home, --memx-url, and --memx-secret values that you used during quickstart when you manage a non-default install.

Clean uninstall

Each uninstall command backs up the target config first, then removes only memX-owned entries. Claude Code and Codex cleanup also stop the managed local service, uninstall the native plugin, remove the local marketplace, and delete the generated marketplace snapshot. OpenClaw cleanup also removes stale memx / memory-memx slot, allow, and entry references, then best-effort uninstalls both current and legacy plugin files if OpenClaw can still see them.

npx -y -p github:NeoLi00/memX memx uninstall openclaw
npx -y -p github:NeoLi00/memX memx uninstall codex
npx -y -p github:NeoLi00/memX memx uninstall claude-code

Add --dry-run to preview, or --config /path/to/config when using a non-default config path.

What memX can do

Remember work over time: project decisions, user preferences, task status, long source segments, and raw evidence stay linked to the original turn.
Connect related things: projects, repos, tools, files, resources, blockers, and outcomes can be represented as entities and graph edges.
Learn collaboration patterns: repeated evidence can become reusable guidance without losing its supporting sources.
Maintain itself: corrections can supersede older facts, stable evidence can be promoted, and stale task state stops competing with current state.
Recall compact evidence: facts, events, state, chunks, relationships, resources, and learned patterns are searched together, then injected as small evidence lines.

File tree

291

NeoLi00/memXView on GitHub

.agents/
  plugins/
    marketplace.json
.claude-plugin/
  plugin.json
.codex-plugin/
  marketplace.json
  plugin.json
.gitignore
.mcp.json
ARCHITECTURE-ch.md
ARCHITECTURE.md
assets/
  agent-logos/
    claude-code.png
    codex.png
    openclaw.png
  memx-agent-support-zh.svg
  memx-agent-support.svg
  memx-architecture-zh.svg
  memx-architecture.svg
  memx-cover-en.svg
  memx-cover.svg
  memx-detailed-architecture-zh.svg
  memx-detailed-architecture.svg
  memx-overview-zh.svg
  memx-overview.svg
dist/
  .runtime/
    index.d.mts
    index.mjs
    sentence_transformers_embedder.py
    src/
      bin/
        memx-hook.d.mts
        memx-hook.mjs
        memx-mcp.d.mts
        memx-mcp.mjs
        memx-server.d.mts
        memx-server.mjs
        memx.d.mts
        memx.mjs
      cli/
        registerCli.mjs
      config.mjs
      db/
        client.d.mts
        client.mjs
        migrations.mjs
        repositories/
          abstractionRepo.mjs
          auditRepo.mjs
          beliefRepo.mjs
          chunkRepo.mjs
          eventRepo.mjs
          factRepo.mjs
          graphRepo.mjs
          maintenanceRepo.mjs
          sourceSegmentRepo.mjs
          stateRepo.mjs
          strategyRepo.mjs
          taskRepo.mjs
          vectorRepo.d.mts
          vectorRepo.mjs
      host/
        connect.d.mts
        connect.mjs
        hookPayload.d.mts
        hookPayload.mjs
        hookRunner.mjs
        httpServer.mjs
        mcpProtocol.d.mts
        mcpProtocol.mjs
        mcpStdio.mjs
        nativeMemoryBypass.mjs
        quickstart.d.mts
        quickstart.mjs
        service.d.mts
        service.mjs
        serviceManager.d.mts
        serviceManager.mjs
        standaloneConfig.mjs
        standaloneQuickstart.d.mts
        standaloneQuickstart.mjs
        transcript.mjs
        uninstall.d.mts
        uninstall.mjs
      identity.mjs
      index.d.mts
      index.mjs
      multilingualLexicon.mjs
      pipeline/
        abstractionJobs.mjs
        abstractionPromotion.mjs
        abstractionRefinement.mjs
        agentEndMessages.mjs
        attributeSlots.mjs
        authority.mjs
        beliefAggregation.mjs
        bootstrapFilter.mjs
        candidateGeneration.mjs
        classify.mjs
        consolidate.mjs
        constants.mjs
        entityAliases.mjs
        entityProfile.mjs
        entityResolver.mjs
        evidenceAssembler.mjs
        evidenceCoverage.mjs
        extract.mjs
        graphPathEngine.mjs
        heartbeatFilter.mjs
        judgeModelConfig.d.mts
        judgeModelConfig.mjs
        llmBudgetAudit.mjs
        maintenanceBatch.mjs
        maintenanceContract.mjs
        memoryObjects.mjs
        memoryObjectsHelpers.mjs
        memoryObjectsProjection.mjs
        messageText.mjs
        normalize.mjs
        outcomeHypotheses.mjs
        policy.mjs
        projectIdentity.mjs
        queryCompiler.mjs
        reasoner.d.mts
        reasoner.mjs
        retrieve.mjs
        retrieveTracing.mjs
        semantic/
          heuristics.mjs
          textSimilarity.mjs
        semantics.mjs
        signalLedger.mjs
        sourceRefs.mjs
        sourceSegments.mjs
        sourceSegmentSemanticExtraction.mjs
        sourceWeighting.mjs
        stateLifecycle.mjs
        strategyHypotheses.mjs
        taskJudge.mjs
        taskSummary.d.mts
        taskSummary.mjs
        turnCapture.mjs
        turnScheduler.mjs
        turnSemanticCompiler.d.mts
        turnSemanticCompiler.mjs
        vectorDocMetadata.mjs
        write.mjs
      plugin-tools.mjs
      runtime.mjs
      search/
        backends/
          embeddingBackend.d.mts
          embeddingBackend.mjs
          ftsBackend.mjs
          hybrid.mjs
        lexical.mjs
      security/
        escaping.mjs
        injection.mjs
        pii.mjs
        scopes.mjs
      support.mjs
      timeouts.mjs
      tooling.mjs
      types.d.mts
      types.mjs
  index.d.mts
  index.mjs
hooks/
hooks.json
  hooks.codex.json
  hooks.json
index.ts
LICENSE
openclaw.plugin.json
package.json
README-ch.md
README.md
scripts/
  clean-dist.mjs
  write-dist-wrappers.mjs
skills/
  memx/
    SKILL.md
src/
  bin/
    memx-hook.ts
    memx-mcp.ts
    memx-server.ts
    memx.ts
  cli/
    registerCli.ts
  config.ts
  db/
    client.ts
    migrations.ts
    repositories/
      abstractionRepo.ts
      auditRepo.ts
      beliefRepo.ts
      chunkRepo.ts
      eventRepo.ts
      factRepo.ts
      graphRepo.ts
      maintenanceRepo.ts
      sourceSegmentRepo.ts
      stateRepo.ts
      strategyRepo.ts
      taskRepo.ts
      vectorRepo.ts
  host/
    connect.ts
    hookPayload.ts
    hookRunner.ts
    httpServer.ts
    mcpProtocol.ts
    mcpStdio.ts
    nativeMemoryBypass.ts
    quickstart.ts
    service.ts
    serviceManager.ts
    standaloneConfig.ts
    standaloneQuickstart.ts
    transcript.ts
    uninstall.ts
  identity.ts
  index.ts
  multilingualLexicon.ts
  pipeline/
    abstractionJobs.ts
    abstractionPromotion.ts
    abstractionRefinement.ts
    agentEndMessages.ts
    attributeSlots.ts
    authority.ts
    beliefAggregation.ts
    bootstrapFilter.ts
    candidateGeneration.ts
    classify.ts
    consolidate.ts
    constants.ts
    entityAliases.ts
    entityProfile.ts
    entityResolver.ts
    evidenceAssembler.ts
    evidenceCoverage.ts
    extract.ts
    graphPathEngine.ts
    heartbeatFilter.ts
    judgeModelConfig.ts
    llmBudgetAudit.ts
    maintenanceBatch.ts
    maintenanceContract.ts
    memoryObjects.ts
    memoryObjectsHelpers.ts
    memoryObjectsProjection.ts
    messageText.ts
    normalize.ts
    outcomeHypotheses.ts
    policy.ts
    projectIdentity.ts
    queryCompiler.ts
    reasoner.ts
    reflect.ts
    retrieve.ts
    retrieveTracing.ts
    route.ts
    semantic/
      heuristics.ts
      textSimilarity.ts
    semantics.ts
    signalLedger.ts
    sourceRefs.ts
    sourceSegments.ts
    sourceSegmentSemanticExtraction.ts
    sourceWeighting.ts
    stateLifecycle.ts
    strategyHypotheses.ts
    taskJudge.ts
    taskSummary.ts
    turnCapture.ts
    turnScheduler.ts
    turnSemanticCompiler.ts
    vectorDocMetadata.ts
    write.ts
  plugin-tools.ts
  runtime.ts
  search/
    backends/
      embeddingBackend.ts
      ftsBackend.ts
      hybrid.ts
      sentence_transformers_embedder.py
    lexical.ts
  security/
    escaping.ts
    injection.ts
    pii.ts
    scopes.ts
  support.ts
  timeouts.ts
  tooling.ts
  types.ts
tests/
  agent-end-selection.test.mjs
  chinese-lexical-retrieval.test.mjs
  embedding-worker-lifecycle.test.mjs
  evidence-packet-selection.test.mjs
  host-service-context.test.mjs
  lifecycle-regressions.test.mjs
  llm-only-entities.test.mjs
  local-embedding-worker.test.mjs
  maintenance-resume.test.mjs
  multi-agent-adapters.test.mjs
  prompt-injection.test.mjs
  quickstart.test.mjs
  service-cli.test.mjs
  setup-config.test.mjs
  standalone-quickstart.test.mjs
  uninstall.test.mjs
tsconfig.json
types/
  openclaw-plugin-sdk-core.d.ts
  openclaw-plugin-sdk-process-runtime.d.ts

FAQ

memx is a Claude Code plugin with 1 hand-picked skill for data work, indexed on Flowy. Install it with the command on its page. It includes memx. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is memx?: memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw
How do I install memx?: Run these in Claude Code: npx -y skills add NeoLi00/memX --agent claude-code. Then prompt normally.
Does memx auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is memx free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.