Your sources and the working truth
Projects, decisions, preferences, methods, open threads and provenance. Allowlisted, versioned, readable Markdown.
From working memory to task-ready context
Keep what is true. Send only what matters.
Unforgetter sits beneath the agents you already use. It captures what each session learns, compiles an approved working truth, serves each task the scoped slice it needs and controls what can become memory afterwards.
The product boundary
A context layer, not another agent platform.
Your sources remain the record of the work. Your agent still performs the task. Unforgetter maintains and compiles the context between them, and never executes anything on your behalf.
Maintain and compile
Resolve what still applies, enforce scope, assemble task-ready context, accept proposals through one publisher.
- No execution, no task relay
- Bounded context, never the whole vault
Claude, ChatGPT / Codex, Cursor and Grok Bot
Each agent receives permitted context through MCP and does the work in its own runtime.
01 · Capture
What an agent learns is captured as a proposal, not lost in a transcript.
At the end of a session, or when an agent notices a change, it submits a bounded proposal: a decision, a correction, a new open thread or a rejected idea, with the evidence behind it.
Input
Session outcomes
What was decided, what stayed open, what was tried and rejected. Structured, small and attributable to the agent that produced it.
Input
Your corrections
When you correct an agent, that correction is a first-class input. It becomes part of the record rather than a message in one tool's history.
Input
Approved sources
Notes, decision records and project material you explicitly allowlist. Raw inboxes, secrets and private notes are excluded by default.
Compatibility
Working now
One memory across your agents
Claude, ChatGPT / Codex, Cursor and Grok Bot use the same MCP contract. Automatic capture from every client is not claimed.
02 · Filter and compile
History goes in. Working truth comes out.
The compiler reconciles new input against the current record. It resolves what supersedes what, keeps rejected proposals so they are not re-proposed, marks freshness and refuses changes to protected areas.
- Memory
Current status, decisions and their reasons, open threads and rejected proposals.
- Methods and skills
How you work: conventions, writing rules, review standards. Portable instructions any agent can follow.
- Policy and scope
What each agent may see and do. Project, client and data-class boundaries enforced by the server.
- Provenance
Which document, which date, which person or agent. Every line can be traced.
- Freshness
When the record was last compiled and which facts are provisional, so stale material is marked rather than trusted.
Compiled
One task bundle
- Small enough to fit the task
- Scoped to what this agent may see
- Marked with provenance and freshness
- Pointers for deeper retrieval instead of a vault dump
Delivered over MCP to the agent doing the task
Supersession, not deletion
A newer decision replaces an older one in the compiled state. The older one stays in history with the date it stopped applying.
Rejected stays rejected
Ideas you turned down are recorded as rejected, so an agent does not rediscover them as fresh suggestions next week.
Protected targets
Goals, policies, permissions and identities cannot be changed by an agent proposal. They only change when you change them.
Single publisher
One consolidation process writes the canonical record. Agents read, search and propose. Nothing else writes.
03 · Scoped retrieval
The useful context is defined by what stays out.
For the task used on the homepage, "Extend the booking flow so a late cancellation is charged against the right date.", the compiler includes current, authorised material and deliberately excludes stale or unrelated material.
Decision
Fee measures against the original booking date
6 Aug · approved by you · supersedes the 22 July draft
Open thread
The capacity split is unresolved
Do not implement around it until it is decided
Method
Money is stored in minor units, never as a float
Your convention, carried into every agent that writes code
Scope
Booking product only
Finance and client material are outside this task
Provenance
3 sources, freshest 6 Aug
Every line traces back to a document you can open
Stale
The rejected 22 July fee proposal
Superseded. Kept for audit, not sent to the agent.
History
Four months of session transcripts
History, not working truth.
Scope
Every other project in your workspace
Out of scope for this task.
A context response is small and bounded: agent identity, the relevant goals and policies, current project facts, open threads, freshness and provenance, plus pointers for deeper retrieval. The whole workspace is never sent to a model.
04 · Continuous maintenance
Agents can suggest. They do not silently decide.
The record stays current because every session feeds it and nothing overwrites it. Proposals are validated, quarantined when their evidence is untrusted, and published by one controlled process.
−Fee measures against the original booking date.
+Fees and refunds measure against the original booking date.
+supersedes: 2026-08-06 · evidence: session 26 Aug 11:05
Publisher checks
- Scope: booking product is in the Codex token's catalogue
- Target: not a protected policy, goal or permission
- Conflict: no newer decision on this target
- Taint: evidence from a trusted session, no injection signal
Published27 Aug · approved by you · served from the next session
- 01
Observe
An agent encounters a decision, correction or new open thread during the work.
- 02
Propose
It submits a bounded change with source, scope and the record it would supersede.
- 03
Govern
The publisher checks authority, protected areas, conflicts and taint. Untrusted evidence can raise scrutiny; it can never lower it.
- 04
Publish
The approved state becomes current. The next agent receives the updated version with provenance intact.
Status
What is live, what is being built, what is not claimed.
| Capability | Status | What you can rely on today |
|---|---|---|
| Versioned Markdown memory | Verified | The canonical record is plain, versioned Markdown you can open anywhere. |
| Same scoped memory across your agents | Compatible | Claude, ChatGPT / Codex, Cursor and Grok Bot connect to the same working memory through MCP. |
| Server-enforced scopes | Working now | Tokens are bound to workspace, trust zone and project catalogue; out-of-scope reads are refused. |
| Provenance and freshness in context | Working now | Every context response carries source references and compile time. |
| Proposal, quarantine, single publisher | Working now | No agent writes canonical memory directly. |
| Revoke, export, deletion | In build | Product functions in the alpha foundation; not yet smoke-tested live. |
| Self-service onboarding, OAuth, teams | In build | Not available yet. Alpha workspaces are connected with you, one client at a time. |
What it is not
Unforgetter does not replace the tools doing the work.
Not an agent runtime
Claude, ChatGPT / Codex, Cursor and Grok Bot and other tools still plan, execute and own their tasks.
Not a transcript dump
History is distilled into working truth and only relevant context is served.
Not a proprietary skill format
Open standards such as MCP and readable Markdown remain the foundation.
Not public self-service yet
Private-alpha workspaces are connected through guided setup while signup and OAuth are in build.
Private alpha
See what changes when the next agent already knows.
Tell us which agents you use and what you want their shared memory to keep track of.