Codex Agent Mem

data-ai MCP Server

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

Verified
data-aidata-ai
6 views27 stars4 forksApache-2.0

Why This Matters

Discovered via github-topic:mcp-server and last synced 3mo ago.

Verified
Source
github-topic:mcp-server
Stars
27
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
6
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (6)

Setup

Observed metrics

Saved

`not_modified`

Scenario

Profile

minimal

6,523

true

Across these reproducible fixtures, repeated operational context was reduced from ~22,950 source tokens to ~1,068 memory-pack tokens, an approximate 95.35% reduction. This is not a universal guarantee; it shows the effect when an agent would otherwise resend the same project continuity. `Tools=4` refers to the pre-session-aware `minimal` profile used by these fixtures. In v1.0.1, `minimal` also includes `mem_session_list`, `mem_scope_resolve`, and `mem_bootstrap_context`, and the `standard` profile exposes 20 tools for broader retrieval, governance, and audit workflows. ### Runtime validation snapshot

standard

full` - explicit read-only audit/debug mode through `--read-only` - compact MCP response text with full `structuredContent` - `known_pack_hash` / `not_modified` continuity-pack reuse - short in-process caching for expensive read tools - lazy SQLite initialization for cheap unused MCP connections - enriched runtime health with profile, mutability, cache, lazy-init, heartbeat, and spawn-storm diagnostics - optional local runtime telemetry through `--telemetry-mode off