Busabase for OpenAI Codex
Knowledge base for Codex
Give Codex durable project knowledge it can read, update, and hand off with every change attributed, diffed, and reversible.
The missing layer
A coding agent can move fast. Project truth should move carefully.
Codex already understands repositories, instructions, and the files in front of it. The harder problem begins after the run: which decisions should survive, which findings are verified, and what should the next agent be allowed to treat as true?
How it works
Four steps from Codex output to trusted context
Read shared context
Codex reads the records, docs, and files relevant to the task instead of reconstructing history from chat.
Propose an update
New findings arrive as a Change Request with the intended field changes and source context.
See the difference
Each Change Request shows exactly what changed. A write key merges it at once; a proposal-only key sends it to the Inbox for a person to approve, revise, or reject.
Reuse the shared record
Future Codex runs start from the current record, while every proposal, merge, and rollback stays traceable.
Review the right change
Review a record update, not a SQL migration
A knowledge update changes a Busabase record or document. A database migration changes an application database through code and deployment tools. Keep migration files in repository review; use Change Requests for shared records and knowledge, so every edit has a diff, an author, and a way back.
Give Codex permission to read the relevant context and propose a record update. Inspect the changed fields and their supporting source. With proposal-only access, proposed values wait for review. After an authorized merge, read the record again to verify the accepted values.
What to keep
Knowledge that should outlive one coding session
Busabase is most useful for context with consequences: information another person or agent will use to make a later decision.
Architecture decisions
Decision, alternatives, evidence, owner, and the conditions that would reopen it.
Verified runbooks
Recovery steps, environment constraints, and the last successful verification.
Release and incident knowledge
What shipped, what failed, what was rolled back, and which evidence supports the conclusion.
Reusable agent workflows
Skills, review checklists, data schemas, and small apps that encode how the team works.
Choose the right layer
Busabase complements repository context. It does not replace it.
Keep code and coding rules close to the repository. Use a versioned knowledge base for shared facts, decisions, and operational context that must remain useful across repositories, agents, and applications.
| Layer | Best for | What makes it trustworthy |
|---|---|---|
| Repository + AGENTS.md | Code, local instructions, tests, versioned configuration | Git history and code review |
| Vector search | Finding semantically related passages | Depends on the source collection and retrieval quality |
| Shared docs | Human-authored explanations and collaboration | Editorial ownership and document history |
| Busabase | Agent-written records, docs, skills, files, and apps | Change Requests with diffs, sources, optional human review, and rollback |
Connect Codex
Use the Skill or connect over MCP
The recommended path is the Busabase Skill, which gives Codex the Change Request workflow as well as the connection. Codex also supports Streamable HTTP MCP and OAuth according to OpenAI's documentation.
MCP connection
codex mcp add busabase --url https://busabase.com/api/mcp
codex mcp login busabase --scopes mcp
Fit check
Use Busabase where shared knowledge needs a history
A strong fit
- Several people or agents reuse the same decisions.
- Agent updates need an owner, a source, or a way to undo them.
- Knowledge spans repositories or business systems.
- You need to reconstruct why a value changed and who changed it.
Use something simpler
- The information is temporary scratch context.
- Git already owns the artifact and code review is enough.
- Nobody else will reuse what the agent writes.
- You need high-volume event storage or vector retrieval only.
Knowledge base for Codex: common questions
Can Codex write directly to Busabase?
The behavior depends on the permission grant. Use Change Request permission for proposal-only work. A writer with write access can create changes that merge immediately; passing autoMerge: false requests review instead. Choose the grant deliberately, inspect the returned Change Request status, and verify the canonical record after a merge.
Does this replace AGENTS.md?
No. AGENTS.md is the right place for repository-local operating rules. Busabase is for versioned knowledge that should be shared across sessions, repositories, people, agents, or applications.
Can Codex use both Busabase Cloud and Desktop?
Yes. Cloud is for shared workspaces and browser-based OAuth. Personal Desktop keeps the workspace on your machine and exposes a local MCP endpoint.
Is Busabase a vector database?
No. Vector retrieval helps find related text. Busabase focuses on structured records, sources, Change Requests, optional review, and full history. The two layers can be used together.
What should the first Base contain?
Start with one consequential workflow: architecture decisions, incident learnings, release readiness, or verified runbooks. Keep the schema small and require a source, owner, status, and last-verified date where those fields matter.
Start with one shared record
Give Codex context your team can trust
Connect Codex, let it propose one useful update, and inspect the diff it leaves behind.