Codex Agent MemorySAFE
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.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://deepwiki.com/MarceloCaporale/codex-agent-mem)
Other languages: Español | Deutsch | Português do Brasil | 中文 | 日本語
Portable, auditable, local-first MCP memory for MCP-compatible AI agents and coding workflows.
codex-agent-mem keeps durable project memory outside the model runtime, compresses continuity into smaller working packs, and carries forward operational state so MCP-compatible AI agents can resume with less repetition, fewer false “done” claims, and more control over what stays in context.
Everything is stored and processed locally by this MCP: SQLite database, FTS index, snapshots, telemetry metadata, and the optional inspector UI. codex-agent-mem does not send your memory, project data, prompts, or telemetry to any external server. MCP clients may still expose tool results to the model or service you configure, so treat retrieved memory as local tool output handed to that client.
Born for Codex and GPT workflows, codex-agent-mem has grown into a portable MCP memory layer for MCP-compatible runtimes including Codex CLI/Desktop, Claude Code, Google Gemini CLI, Qwen Code workflows using Ollama models, and other local or third-party CLI agent stacks. Validation is tracked per client/runtime and evidence level. Model-specific details stay in the validation docs so the README can describe the public surface without overclaiming one runtime.
codex-agent-mem lives locally, keeps memory auditable and pull-based, and does not send your stored memory to any external service.
Public baseline. Built in small, testable slices and still evolving, but already aligned for real use.
What’s new in v1.0.x
- v1.0.2 fixes a proje
b5dfa85dc031OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add codex-agent-mem -- uvx codex-agent-mem
{
"mcpServers": {
"codex-agent-mem": {
"command": "uvx",
"args": [
"codex-agent-mem"
]
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
mem_completion_check | read | |
mem_context_pack | read | |
mem_health_runtime | read | |
mem_open_work | read | |
mem_snapshot_create | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (10)
token = "MCP_DIAGNOSTIC_NOTE_20260429_2255"
http://127.0.0.1:37770/ui
http://127.0.0.1:37770/ui
http://127.0.0.1:37770/ui
http://127.0.0.1:37770/ui
http://127.0.0.1:37770/ui
`codex-agent-mem` runs in Claude Code as a standard MCP stdio server. It does not install session-start hooks, stop hooks, or automatic post-turn summarization. Memory is retrieved on demand through M
`codex-agent-mem` läuft in Claude Code als normaler MCP-stdio-Server. Es installiert keine Session-Start-Hooks, Stop-Hooks oder automatische Post-Turn-Zusammenfassungen. Speicher wird bei Bedarf über
`codex-agent-mem` は Claude Code で標準 MCP stdio server として動作します。session-start hook、stop hook、自動 post-turn 要約はインストールしません。メモリは `mem_context_pack`、`mem_search`、`mem_open_work`、`mem_completion_check` などの MC
`codex-agent-mem` 在 Claude Code 中作为标准 MCP stdio server 运行。它不会安装 session-start hook、stop hook,也不会做自动 post-turn 总结。内存只在需要时通过 `mem_context_pack`、`mem_search`、`mem_open_work` 和 `mem_completion_check` 等 MC
Gates applied: no_behavioural_pass.
b5dfa85dc031full audit observations/trust-audit/mcp-server/marcelocaporale__codex-agent-memory.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | b5dfa85dc031 | SAFE | B | 89 | first audit |
Questions
What is the Codex Agent Memory 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.
What tools does Codex Agent Memory expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Codex Agent Memory safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Codex Agent Memory need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (b5dfa85dc031), read on 2026-10-08. The repository is watched and re-audited when it changes.