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 .
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 49 cited facts, 2 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- File-backed ~/.codex/memories + Chronicle vendor fix
- Tier
- T1
- Section
- Coding-agent memory
- Created
- searched not found fix
- Latest release
- 0.165.0 (2026-10-27) (Codex CLI) vendor fix
- License
- Apache-2.0 (Codex CLI; cloud agent proprietary) repo fix
- GitHub
- openai/codex — ~128k stars, last commit 2026-10 repo fix
- Funding
- total n/a; latest round $122B committed at $852B post-money (2026-04) third-party fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- python, typescript vendor fix
- Protocols
- mcp-client, opentelemetry vendor fix
- Developer activity
- OpenRank 885.42 (12-mo avg 407.37) · 11814 participants — 2026-09 third-party fix
Memory 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…
Alternatives to OpenAI Codex (cloud agent) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other coding-agent memory in the catalog, ranked by inbound references.
- 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.
- 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. Acquired by Harness (2026-10-08): Harness bought select Augment Code assets, including Cosmos, the Auggie CLI and the Context Engine, and the team joined Harness. augmentcode.com now leads with Cosmos, a software-factory agent platform.
- Letta Code T3
Letta's stateful coding-agent harness: agents rewrite their own memory blocks and skills, version context in git via MemFS (syncable to GitHub) and reflect via a periodic /sleeptime 'dreaming' process. from Letta (MemGPT) team. letta-ai/letta-code is now the main Letta source (harness, terminal UI, App Server, channels); the Letta V1 API server was retired to the archive branch of letta-ai/letta.
- Replit Agent T1
No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory relies on filesystem + agent-written notes.
- agentmemory (rohitg00) T3
Self-hosted persistent memory layer that captures coding-agent activity and recalls it in later sessions, positioned on public benchmark results. #7 in TeleAI Awesome-Agent-Memory
Sources (48 cited facts, 2 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is File-backed ~/.codex/memories + Chronicle vendor
- What it does & what's distinct Memory under ~/.codex/memories/ : summaries, durable entries, recent-input logs, support… vendor
- Claims / benefits User-scoped across sessions on the same machine. Not available in EEA/UK/Switzerland. vendor
- Modalities text vendor
- Latest release 0.165.0 (2026-10-27) (Codex CLI) vendor
- License Apache-2.0 (Codex CLI; cloud agent proprietary) repo
- GitHub openai/codex — ~128k stars, last commit 2026-10 repo
- Mindshare OpenAI Codex docs + sustained HN/X discussion since Sept 2025 cloud-agent launch; ~/.cod… vendor
- Funding total n/a; latest round $122B committed at $852B post-money (2026-04) third-party
- Customers / scale 1000+ ppl No named enterprise customers on memory feature vendor
- Pricing Included in ChatGPT Plus/Pro/Business/Edu/Enterprise plans (memory feature) vendor
- Compliance SOC 2 Type II; ISO 27001; HIPAA-eligible; GDPR; CCPA; FERPA vendor
- Data handling Enterprise/API: never trains by default; infrastructure encrypted in transit and at rest… vendor
- Deployment Both (cloud agent via ChatGPT platform + CLI tool local) vendor
- HQ US (San Francisco) vendor
- Founders / pedigree OpenAI; Sam Altman (CEO), Greg Brockman, Ilya Sutskever, Wojciech Zaremba, John Schulman vendor
- Memory volume / scale internal — undisclosed vendor
- API surface REST (OpenAI Responses API; Codex CLI wraps it) vendor
- Backend storage custom vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC vendor
- Embedding model locked vendor
- Consistency strong vendor
- Versioning immutable append-log vendor
- Tombstoning append-only no delete vendor
- Schema evolution free-form / no schema vendor
- Namespace primitives hierarchical vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy consolidation/summarization vendor
- MCP support native (first-party) vendor
- Validated verticals coding agents only vendor
- Time to running <10min (ChatGPT Pro / Plus + Codex) vendor
- Anti-fit not for non-coding tasks vendor
- Optimised for file-backed memory under ~/.codex/memories vendor
- Adjacent infrastructure self-contained Codex environment vendor
- Pros Tight integration with the OpenAI model + tool-use roadmap; benefits directly from front… vendor
- Cons Memory is shallow — primarily session-scoped; no long-running project memory yet. vendor
- Project & sources memories docs Chronicle vendor
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":13770.5,"as_of":"2026-09","openrank_12mo":407.37,"openrank_current":885.42,"… third-party
- sdk-languages python,typescript vendor
- protocol-support mcp-client,opentelemetry vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-29
- Latest release “0.161.0 (2026-10-07) (Codex CLI)” → “0.165.0 (2026-10-27) (Codex CLI)” source
- 2026-10-22
- License “not applicable — not OSS” → “Apache-2.0 (Codex CLI; cloud agent proprietary)” source
- Latest release “not applicable — not OSS” → “0.161.0 (2026-10-07) (Codex CLI)” source
- Funding / ownership “OpenAI $57B+ raised; $300B+ valuation” → “total n/a; latest round $122B committed at $852B post-money (2026-04)” source