OpenAI Codex (cloud agent)
https://developers.openai.com/codex/memories
Memory under ~/.codex/memories/ : summaries, durable entries, recent-input logs, supporting evidence — generated in background after sessions go idle. Chronicle (opt-in macOS preview) uses screen-capture to seed memory. Off by default; opt-in via config.toml .
At a glance
- Type
- File-backed ~/.codex/memories + Chronicle
- Tier
- T1
- Section
- Coding-agent memory
- Created
- searched not found
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Included in ChatGPT Plus/Pro/Business/Edu/Enterprise plans (memory feature)
- Funding
- OpenAI $57B+ raised; $300B+ valuation
Taxonomy
- storage
- file
- retrieval
- injection
- persistence
- long-term
- update
- consolidation
- unit
- summary
- governance
- inspectable
- conflict
- none
When to use
Optimised for: file-backed memory under ~/.codex/memories
Anti-fit: not for non-coding tasks
Pros & cons
Pros
Tight integration with the OpenAI model + tool-use roadmap; benefits directly from frontier model improvements.
Cons
Memory is shallow — primarily session-scoped; no long-running project memory yet.
Claims & capabilities
User-scoped across sessions on the same machine. Not available in EEA/UK/Switzerland.
Technical surface
- API surface
- REST (OpenAI Responses API; Codex CLI wraps it)
- Backend storage
- custom
- Deployment
- Both (cloud agent via ChatGPT platform + CLI tool local)
- Embedding model
- locked
- Multi-tenancy
- hard-isolation
- MCP
- native (first-party)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare OpenAI Codex (cloud agent) with…
Similar systems
Other coding-agent memory in the catalog, ranked by inbound references.
- Aider T2
Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries static preferences.
- Augment Code T1
Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. MCP endpoint exposes the graph.
- Bolt.new (StackBlitz) T2
In-browser WebContainer (Rust-backed shared memory) is the implicit state store. No dedicated memory abstraction — project files are the state. Team plan adds shared workspaces + GitHub integration.
- Continue.dev Memory MCP T2
Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP rather than native to the Continue core. Scope depends on MCP server deployment (local or shared).
- Devin (Cognition) T1
Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads past session trajectories for self-improvement; writes notes for recurring scheduled tasks.
- Lovable T2
Long-term context stored as files in /docs that the agent reads on each session. Agent Mode (default since July 2025) holds working context within session but doesn't persist cross-session beyond filesystem state.