Keep your agents working beyond the context window
CtrlB Recall keeps commands, errors, decisions and tool results searchable across sessions. Your agents find the context they need to continue long tasks, even after compaction.
The self-serve version is free. One binary, no account.
Agent context
- #38PromptKeep refund retries under 3.
- #41bash
pytest tests/refunds -k retry - #42Result
FAILED test_retry.py::test_cap - #57Edit
src/refunds.py
- #90PromptWhich test failed before the fix?
- #91Search
search_sessions("retry.py") - #92AnswerFound at #42: test_cap in test_retry.py failed.Exact row
CtrlB Recall
4 rows kept- #38PromptKeep refund retries under 3.
- #41bash
pytest tests/refunds -k retry - #42Result
FAILED test_retry.py::test_capHit - #57Edit
src/refunds.py
81–94% vs 22–35%
Detail questions right after compaction
Summary only: 22 to 35%. CtrlB Recall: 81 to 94%. Solid bars show the low value; lighter extensions show the high value. Scale: 0 to 100%.
0 model calls
To build memory. Searchable in 5.5 s.
Model calls to build memory: Mem0 632, CtrlB Recall 0. Linear scale: 0 to 632 calls; zero is a 3 pixel stub. Recall is searchable in 5.5 seconds.
135× faster
Search at 100× the record, against grep
Search at 100 times the record: grep 189 seconds, CtrlB Recall 1.4 seconds, or 135 times faster. Linear scale: 0 to 189 seconds; Recall has a minimum 3 pixel stub.
Recover what happened, not just the summary
A compaction summary keeps the outcome. CtrlB Recall keeps the steps that led to it.
After compaction
“The previous test failed.”
The summary keeps the outcome. The command, the error and the fix are gone.
Kept: 1 line
With CtrlB Recall
- Command
pytest tests/auth/test_token.py -x- Error
FAILED test_refresh: expected 401, got 200- Change
auth/token.py: check expiry first
Source: session 7f3a2c, rows 4,182 to 4,190
Memory that decides when it writes has to guess which details will matter. CtrlB Recall keeps every row, so the agent decides at read time, when it knows the question.
How CtrlB Recall works
Three steps, and your agent runs all of them through hooks and tools.
- 01
Capture
Save messages, tool calls and results from connected agent sessions.
- 02
Keep
Keep the original record while the agent's context is compacted.
- 03
Recall
Find earlier commands, errors and decisions through the agent's tools.
Your agent
Claude Code or Codex runs as usual.
Subagents too.
Hooks upload
At the end of each turn, before compaction and at session end.
Secrets are redacted first.
Your bucket
One row per message, tool call and tool result.
Open Parquet in S3, GCS or Azure Blob.
Recall tools
The agent searches the record over MCP.
At session start, the agent is told: search before you answer.
What your agents can ask
Four MCP tools read the record, and each reply stops at 12,000 characters.
search_sessionsFind a word across sessions
It finds a whole word in messages, commands and results, in current and past sessions. It returns 10 hits by default, 25 at most.
search_sessions(term="refunds.py")You get: Hits with session, row number and a 300-character snippet.
find_commandFind a command you ran before
It returns every past tool call whose command contains your text, newest first. It returns 10 by default, 25 at most.
find_command(command="pytest tests/refunds")You get: The total, then session, row and command for each match.
next_actionsSee what happened next
It returns the result of one tool call, then the next three calls and their results. Text and thinking rows are skipped.
next_actions(session_id="7f3a91c2", seq=41)You get: What the agent did after a failure, and whether it worked.
fetch_recordsOpen the rows around a hit
It returns the rows of a range in order. A range holds 50 rows at most, and each body is cut at 4,000 characters.
fetch_records(session_id="7f3a91c2", seq_from=38, seq_to=42)You get: The exact rows, with the full length of any cut body.
Recover more details after compaction
Four models, two families, asked at real compaction points.
Detail questions right: summary only against CtrlB Recall
| Model | Summary only | CtrlB Recall |
|---|---|---|
| Claude Haiku 5.5 | 23% | 85% |
| Claude Sonnet 5.5 | 22% | 89% |
| GPT-6 Luna | 29% | 81% |
| GPT-6.1 Sol | 35% | 94% |
Better recall doesn't always need a bigger model
Claude Haiku with CtrlB Recall answered more than Claude Sonnet with only the summary.
- 70 to 72%Cross-session lookup with CtrlB Recall, small models. Summary only answered none.60 questions per family, no session named.
- -2 to +6 ptsRecall change when the summary is dropped, with CtrlB Recall and the search instruction on. Each answer cost less.Compaction pauses a Claude Code session for a median of 61 s.
With CtrlB Recall on both sides, the larger model is level or ahead. Haiku 5.5 trails Sonnet 5.5 by 4 points, not significant. GPT-6 Luna trails GPT-6.1 Sol by 13.
How CtrlB Recall compares with Mem0
Mem0 keeps short extracted memories. CtrlB Recall keeps the full record and searches it.
Turn 90 asks
Which test failed before the fix?
Compaction summary
Decides at compaction
Fixed the retry tests in refunds. Next: update the docs.
29%detail recall
Extracted memory
Decides when it writes
- Prefers pytest
- Refunds live in src/refunds.py
- Retries capped at 3
37%detail recall
CtrlB Recall
Decides when your agent asks
- #41bash
pytest tests/refunds -k retry - #42Result
FAILED test_retry.py::test_cap - #57Edit
src/refunds.py
81%detail recall
Mem0: 37 to 44%. CtrlB Recall: 81 to 94%. The solid bars show the low value and lighter extensions show the high value.
Mem0: 632 calls, $3.92. CtrlB Recall: 0 calls, $0. Heights use a linear scale; zero is a 3 pixel baseline stub.
Mem0: 3.6 hours. CtrlB Recall: 5.5 seconds. Heights use a linear scale; Recall is shown as a 3 pixel baseline stub.
Find answers across your team's agent sessions
Recover past investigations, commands and fixes without knowing which session holds them.
- Which command fixed this error?
- Why did we change this configuration?
- What did the other agent already try?
Search the sessions you're authorized to access.
- You see your own sessions by default. Admins see everyone’s.
- Rows are open Parquet files in your S3, GCS or Azure Blob bucket.
- Search stays fast as the record grows.
| Record size | CtrlB | grep over files |
|---|---|---|
| 1× (170k rows) | 147 ms | 450 ms |
| 10× (1.7M rows) | 494 ms | 4.1 s |
| 100× (17M rows) | 1.05 s | 165 to 408 s (9 of 120 calls finished) |
| Session | User | Harness | Last activity | Turns | Tool calls | Errors |
|---|---|---|---|---|---|---|
Keep refund retries under 3.7f3a91c2 · billing-api · fix/retry-cap | priya@acme.dev | Claude Code | 10:42 | 46 | 112 | 2 |
Add idempotency keys to the refund endpointc41e08b7 · billing-api · main | dan@acme.dev | Codex | 10:15 | 31 | 74 | 0 |
Why does the invoice export time out?9b20d4ae · invoices · perf/export | priya@acme.dev | Claude Code | 09:58 | 18 | 40 | 1 |
Write the migration for refund_attemptse83f5c10 · billing-api · fix/retry-cap | sam@acme.dev | Claude Code | 09:31 | 22 | 51 | 0 |
Your agent history, in your own cloud
CtrlB Recall stores session records in your own bucket as open Parquet. The CtrlB plugin connects Claude Code and Codex. Other agents connect through MCP or the API.
Claude Code
Codex
The self-serve version is free. One binary, no account.
Common questions
What does CtrlB Recall keep?
It keeps one row for each message, tool call and tool result. Each row has the role, the shell command, the time and the session. Subagents are included. Nothing is updated or deleted.
How is it different from extracted memory?
Extracted memory decides what to keep when it writes. CtrlB Recall keeps every row, and your agent decides what matters when it asks. With GPT-6 Luna on 100 detail questions, extracted memory scored 37% and Recall scored 81%. Against open-source Mem0 2.2.1, Recall answered 81 to 94% of detail questions and Mem0 answered 37 to 44%.
How is it different from compaction?
Compaction writes a summary and drops the rows. In our Claude Code sessions, 6% of exact answers were still in the context after compaction. Exact means a path, number, error line or command. Recall keeps the rows, so the agent can find them.
Where does my data live?
Rows are open Parquet files in your S3, GCS or Azure Blob bucket, and SQL can query them. In the free self-serve version, rows stay in SQLite under ~/.ctrlb on your machine. Hooks redact text that looks like a secret before upload. The redaction patterns match common key and token shapes and are not a guarantee.
Who can see whose sessions?
You see your own sessions by default. Admins see every user's sessions. Editors and Admins can upload sessions from their agents.
What does it cost, and how fast is it?
At 100× the record, CtrlB search took a median of 1.05 s. Grep over the files finished 9 of 120 calls. Haiku 5.5 with Recall costs about 1/15 as much per question as Sonnet 5.5. The self-serve version is free and runs on your machine. Book a demo for team use.
Which agents does it work with?
Claude Code and Codex, through the CtrlB plugin and hooks. The hooks upload at the end of each turn, before compaction and at session end.