01
Click endurance
29k
saved
42.7%
less token use
91k baseline to 62k with Kairn.
Private beta
kairn
Give coding agents a context governor.
Kairn runs locally beside your agent. It decides when to route source, shrink context, stay silent, or ask for evidence, so long coding sessions stay focused and cheaper.
Local-first. Index and session memory stay on your machine.
Less waste. Repeated and irrelevant context gets filtered before the agent sees it.
Agent-ready. Works through Codex session hooks or local MCP.
What it does
Kairn turns repo context into a control layer.
01
Find the source files the agent should start with.
02
Keep repeated context out of long sessions.
03
Ask for missing evidence instead of guessing.
04
Work through Codex session hooks or local MCP.
Evidence snapshot
Lower token use, quality-gated.
Validated slices
8
fresh, endurance, MCP, official
Median reduction
42.7%
clean rows shown
Official tasks passed
5/5
small SWE-Pro pilot
Endurance suites
4
long-session evidence
02
Node SemVer endurance
11k
saved
16.4%
less token use
70k baseline to 58k with Kairn.
03
OpenLibrary SWE-Pro
12k
saved
54.2%
less token use
22k baseline to 10k with Kairn.
The savings shown here only count when the task still passes. Separate evaluator rows also show Kairn improving outcomes when better source focus matters.
Beta paths
Bring it to the agent you already use.
Codex CLI
The most-tested private beta path for terminal workflows.
MCP
The portable path for editors, extensions, and agent UIs.
Telemetry
Optional aggregate feedback that helps improve routing without uploading code.
Privacy
Local-first by design.
Your source, prompts, diffs, filenames, repo names, branch names, and raw outputs stay local by default. Beta telemetry is opt-in and aggregate-only.
Private beta