Skip to main content
Glama
Sign In
deenesjakoruzh
ctx-memory

ctx-memory

by GhadiSaab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

ctx-memory

Persistent memory for LLM coding agents — Claude Code, Codex, Gemini CLI, OpenCode.

When you start a new session, the agent already knows what you worked on last time: decisions made, files touched, errors hit, conventions learned. No cloud. No telemetry. Everything lives in a local SQLite database at ~/.ctx-memory/store.db.

How it works

Session starts
      │
 Shell wrapper intercepts 'claude' (or codex/gemini/opencode)
      │
 MCP server starts alongside — injects prior context, exposes memory tools
      │
 During session: hooks fire on every tool call, messages buffered
      │
 Session ends (clean exit / Ctrl-C / crash)
      │
 Layer 1 → Layer 2 → Layer 3 pipeline runs
      │
      ├── Layer 1: extract weighted messages, events, decisions, errors, keywords
      ├── Layer 2: compress to ≤500-token digest, store in DB
      └── Layer 3: merge digest into project memory doc (markdown)

Next session: agent reads prior context automatically

Related MCP server: remem

Install

npm install -g ctx-memory
ctx-memory setup

The setup wizard:

  1. Detects which tools are installed (claude, codex, gemini, opencode)

  2. Asks which ones to integrate

  3. Writes hook configs for each tool

  4. Creates wrapper symlinks in ~/.ctx-memory/bin/

  5. Adds ~/.ctx-memory/bin to your PATH via ~/.bashrc / ~/.zshrc

Restart your shell (or source ~/.bashrc), then use your tools as normal — memory is automatic.

Commands

ctx-memory setup                        # interactive setup wizard
ctx-memory status                       # show configuration and stats
ctx-memory projects list                # list all projects
ctx-memory projects show <name>         # print full memory doc for a project
ctx-memory projects forget <name>       # reset memory (keeps sessions)
ctx-memory projects forget <name> --hard  # delete all sessions + data

MCP server

The MCP server runs as a sidecar alongside each tool session and exposes six tools:

Tool

Description

store_message

Buffer a conversation message for processing at session end

store_event

Record a tool call event (file edit, bash command, etc.)

search_context

Search past sessions by semantic similarity or keywords

get_project_memory

Return the full project memory doc

list_sessions

List recent sessions with goals and outcomes

end_session

Finalize a session and run the Layer 1 → Layer 2 → Layer 3 pipeline

To use the MCP server standalone with Claude Code, add to ~/.claude/settings.json:

{
  "mcpServers": {
    "ctx-memory": {
      "command": "node",
      "args": ["/path/to/ctx-memory/dist/src/mcp/index.js"]
    }
  }
}

Architecture

src/
  cli/        — setup wizard, status, projects commands
  db/         — SQLite schema + CRUD (projects, sessions, events, digests, memory)
  layer1/     — pure message/event processing → weighted Layer1Output
  layer2/     — digest compression to ≤500 tokens → Layer2Digest
  layer3/     — merge digest into ProjectMemory markdown
  mcp/        — MCP server (handlers + stdio entry point)
  wrapper/    — shell wrapper (intercepts tool invocation, manages session lifecycle)
  hooks/      — hook config writers for Claude / Gemini / OpenCode

Key constraints:

  • All Layer 1/2/3 functions are pure — no I/O, never throw

  • Digests stay under 500 tokens

  • Vector search uses all-MiniLM-L6-v2 embeddings via sqlite-vec (384-dim)

  • Single SQLite DB, WAL mode, foreign keys on

Development

npm run build       # tsc → dist/
npm run dev         # tsc --watch
npm run test:run    # vitest (single-shot, 476+ tests)
npm test            # vitest (watch mode)

DB path defaults to ~/.ctx-memory/store.db. Override with CTX_MEMORY_DB_PATH.

License

MIT

Available Tools

6 tools
end_sessionC

Signal session end — runs Layer 1→2→3 pipeline, stores digest, updates project memory.

Inputs: outcome (required), project_id (required), session_id (required), exit_code.

get_project_memoryC

Return the full project memory document (architecture, conventions, recent work, known issues).

Inputs: project_id.

list_sessionsC

List recent sessions for a project with their goals and outcomes.

Inputs: limit, project_id.

search_contextB

Search past sessions for context relevant to a query. Uses embedding similarity, falls back to keyword search.

Inputs: query (required), limit, project_id.

store_eventC

Record a tool call event (file edit, bash command, etc.) for the current session.

Inputs: tool (required), session_id (required), args, result, +1 more.

store_messageC

Buffer a conversation message for session-end processing.

Inputs: role (required), index (required), content (required), session_id (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    B3.3/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: session lifecycle (end_session), memory retrieval (get_project_memory, list_sessions, search_context), and data recording (store_event, store_message). No overlap in functionality.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case, e.g., end_session, get_project_memory, store_event. The naming is predictable and uniform.

    Tool Count5/5

    With 6 tools, the server covers core memory management operations without bloat. The count is well-scoped for the domain of session context and project memory.

    Completeness5/5

    The tool surface covers the full typical lifecycle: recording events/messages, searching and retrieving context, listing sessions, and finalizing sessions with memory updates. No obvious gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers