v0.1 · live now on macOS & linux

You’re burning tokens.

ctxpilot stops the bleed.

Your agent re-reads the same files every session. That’s 30-50% of your input tokens — wasted. ctxpilot eliminates the waste for ~$0.001/session.30-50% less spend. 200× fewer tokens per lookup. ~$0.001 per session.

~/repo · ctxpilot
$
 
 
 
 
 
 
 

Current beta stack

Claude CodeanthropicLocal MCPstdioSQLitelocalBeta APIlicense

The problem

You ship the same fix on Tuesday.
You pay for it again on Friday.

Every new session, your AI agent starts from zero. It re-reads package.json for the 47th time. It re-derives the architecture you already explained. It re-discovers the bug you fixed last week. You pay for every byte of that amnesia.

47×
package.json reads

A typical mid-size repo, 30 days of Claude Code use. The same file, parsed and tokenized 47 separate times.

$0.34
cost per session

Average ‘fix one bug’ session today. ~65% of that is the agent re-reading files it already understood.

$18-50
wasted per month

Per developer. Per project. Compounds every time you bring a new agent online.

tokens saved·waste detected·ROI measured·files deduped·sessions traced·models routed·local first·tokens saved·waste detected·ROI measured·files deduped·sessions traced·models routed·local first·

How it works

Install once. It runs.

The beta installer writes Claude Code hooks, starts a Codex CLI session watcher, boots the local worker, and registers the MCP server. Then you go back to coding. ctxpilot watches, learns, and serves answers when asked.

01 / 04

Hook

Every tool call from Claude Code and OpenAI Codex CLI fires a local event. Nothing leaves your machine.

[hook] tool_use
  agent:  claude | codex
  tool:   edit_file
  file:   auth.ts
02 / 04

Extract

Git diffs, test output, command results — parsed by deterministic rules. Zero AI calls for 90% of memories.

extracted:
  file_edit     0.91
  test_pass     0.86
  command_ok    0.93
03 / 04

Store

Content-hashed and stored in local SQLite. Auto-deduplicated. Confidence decays over time.

db:    ~/.contextpilot/contextpilot.db
hash:  e7f3a1
dedup: hit (existing)
conf:  0.91 → 0.91
04 / 04

Recall

15 tokens instead of 5,000. Same answer. Agent calls contextpilot_search mid-session and gets the compact, ranked result.

→ "JWT validation
   added session 42.
   middleware.ts:47"
→ 15 tokens · 2 hits

Side-by-side

Same bug fix. Two-thirds fewer tokens.

Left: what you pay today. Right: after npx ctxpilot install.

Without ctxpilot

session 47 — auth bug fix
> Read src/auth/middleware.ts (3,200 tokens — read 46× before) > Read src/auth/jwt.ts (2,800 tokens — read 31× before) > Read src/config/auth.ts (1,400 tokens — read 28× before) > Read package.json (900 tokens — read 47× before) > Read tsconfig.json (600 tokens) ...then starts the actual work Session cost: $0.34 Wasted on re-reads: $0.22

With ctxpilot

session 47 — auth bug fix
> ctxpilot_search("auth middleware") → "JWT validation added session 42. middleware.ts:47 checks exp claim." (15 tokens) > Edit src/auth/middleware.ts (knew the file already) > Run tests — all pass Session cost: $0.12 Memory cost: $0.001 Saved: $0.22 (65%)

65% fewer tokens. Same result. Every session.This is one bug fix. Multiply by ~80 sessions/month.

The math

Your bill, reduced.

What an active developer on Claude Opus saves in a month — 150 sessions, multi-repo workflow. Heavier usage scales linearly. Run your numbers ↓

0%
of input tokens

can vanish into amnesia today — your agent re-reading the same files. ctxpilot keeps the work the agent did yesterday.

$0
back per year

For an active Opus user at 150 sessions/month. That’s $54/mo straight off your Anthropic bill — at $9/mo Pro you net $540/year.

0×
cheaper per lookup

15 tokens to recall a fact from memory. 3,200 tokens to re-read the file. Every. Single. Session.

Projected launch model · replace with your local measured savings after install

Calculator

What you’re actually spending.

Plug in your usage. Real model pricing as of May 2026. Assumes ~75/25 input/output ratio and a projected 42% re-read rate.

Your usage

/ inputs
80

A session = one AI coding task, end-to-end.

60.0K

Total input + output tokens. Default reflects a typical mid-size repo.

Anthropic · $3.00 / $15.00 per M

What ctxpilot saves you

/ output
Net savings · per month
$4.46/ month
$53 per year · 56× ROI on memory overhead
Current monthly spend
$28.80
Wasted on re-reads
$4.54
Tokens wasted / month
1.51M
ctxpilot overhead
$0.08
Annual spend (today)
$346
Annual waste (today)
$54
> per-session input: 45.0K tok · $0.135 output: 15.0K tok · $0.225 total cost / session: $0.360
Recommended plan
Free

Stay on Free. You'll save $4.46/mo at $0 cost. Upgrade to Pro ($9/mo) once you have multiple repos.

Disclaimer: estimates are projections until your local install has measured sessions. Your savings depend on repo size, agent, and how often you start fresh sessions.

Memory engine

Eliminate repeated reads automatically.

Deterministic extraction from git diffs, test output, and commands. No AI calls for 90% of memories. Content-addressed deduplication. Automatic confidence decay. Secret scanning built in.

ctxpilot search
$ ctxpilot search "stripe webhook" file_edit 2d added validation webhook.ts (0.94) test_pass 2d stripe tests: 12 passed (0.91) 2 results, 30 tokens

CLI savings reports

Get a waste receipt from the terminal.

Repeated-read detection, savings proof, project waste reports, and projected monthly savings from local data. No browser app required — your data stays on your machine.

contextpilot savings
$ contextpilot savings Credits saved $0.0006 Tokens saved 216 Repeated reads 1 Top savings proof package.json: 264 raw - 48 compact = 216 net

Project waste analyzer

Find expensive context before agents reread it.

Analyze instruction files and project context weight without storing source bodies. The report shows what is likely costing credits every time an agent starts.

ctxpilot analyze .
$ ctxpilot analyze . Instruction tokens: 18,420 Cost per AI run: $0.0553 Monthly estimate: $4.42 Instruction files high CLAUDE.md 12,100 tokens med AGENTS.md 4,900 tokens

MCP integration

75 tokens instead of 15,000. Same answer.

Four MCP tools any compliant agent can call mid-session — Claude Code and OpenAI Codex CLI both supported in v1: contextpilot_search, contextpilot_get, contextpilot_remember, contextpilot_status. The agent gets the result without re-reading five files.

claude code + codex · mcp
// Claude Code / Codex call: contextpilot_search({ query: "auth bug", limit: 5 }) // Returns 75 tokens // instead of re- // reading 5 files // (15,000 tokens) // 200× reduction

Local-first & private

Your code never leaves your machine.

Memory is stored in a local SQLite database. No cloud sync. No telemetry. No analytics calls. Secret scanner blocks API keys before they’re ever indexed.

  • SQLite on your local disk.
  • Secret scanner — never indexes API keys.
  • No product telemetry in the local worker.
  • Uninstall keeps data unless you choose --delete-data.
  • Core capture works without cloud sync.

Install

30 seconds. No signup.

install
$ npx ctxpilot install

Writes hooks into your agent, starts a local worker on port 3848, registers the MCP server, and keeps reports available from the CLI.

Free tier saves you money from session one · no credit card

Pricing

Free already saves you money.

ctxpilot Free pays for itself the moment you install it. Paid plans are in customer beta while licensing, checkout, and support workflows are finalized. Run the numbers ↑

Free

Solo dev · one repo

$0forever
  • 1 project
  • 100 memories
  • Full token savings
  • CLI savings reports
  • MCP + CLI
  • No card · no trial
Install free

Pro

Solo dev · many repos

recommended
$9per month
  • Unlimited projects
  • 5,000 memories per project
  • Waste detection
  • Full CLI analytics
  • Priority beta support
  • License activation

Builder

Heavy use · 150+ sessions/mo

planned
$19planned / mo
  • Everything in Pro
  • Unlimited memories
  • Advanced waste reports
  • Git-aware insights
  • Session timelines
  • Custom memory rules
Join waitlist

Team

Shared memory · whole team

planned
$29planned / seat
  • Everything in Builder
  • Shared team memory pool
  • Per-seat access controls
  • Cross-repo memory policy
  • Audit exports
  • Dedicated support
Join waitlist

Enterprise: self-hosted pilots · compliance review · custom support · contact us

One command from here

Stop paying for amnesia.

$npx ctxpilot install