The right model, at the right price, with a memory that holds
— Chaser orchestrates Claude and proves it, token by token

Chaser is a 100% local orchestrator that sits between you and the Anthropic API: it routes each task to the cheapest model that can handle it, and hands off context between sessions so you stop re-explaining your codebase every morning. No data ever leaves your machine.

⬇ Free check — Chaser Check Buy Chaser →

Chaser Check is free: it installs the prerequisites and verifies your machine is ready. The full product activates after purchase. Windows 10/11 — a macOS version is in preparation.

The problem

Your Anthropic bill keeps climbing because a deep model gets called for work a cheaper one could have handled just fine. Multiply that across a team, or across a few months of daily use, and the API line item stops looking like a rounding error.

Then a session crashes mid-task, or you simply open a new one the next morning — and every decision, every fixed bug, every bit of accumulated context is gone. You start over, explaining the same architecture and the same conventions you explained yesterday.

What makes it different

💬 It protects your chat quota, not just your API bill

Most tools only chase the API invoice. Chaser also compresses tool outputs before they ever enter the conversation, so your Claude Code subscription quota lasts longer. Two separate wallets, two separate defenses.

🔍 Honest measurement, not marketing numbers

10% of all compressions are randomly held out and checked, never cherry-picked. Every result is sealed in a hash-chained, Merkle-rooted log you can audit yourself — not "our own counters".

🧠 Memory that survives your sessions

Context handoff between Claude Code sessions happens automatically, with no manual re-explaining. Long-term memory is organized in layers, so a new session starts on a distilled summary instead of a wall of raw facts.

🛡️ A real safety shield, not a keyword filter

Chaser blocks dangerous commands like rm -rf ~ and curl | sh, and catches hardcoded secrets before anything executes. It runs before the action, not after the damage.

🧪 Engineering at the research frontier

Contextual bandits drive model routing, semantic caches are gated instead of blindly trusted, and savings are backed by anytime-valid statistics. Builds are reproducible and ship with an SBOM.

🔒 100% local, start to finish

Your prompts, your API key and your data never leave the machine. The Cockpit dashboard runs on localhost, and uninstalling from Windows is a clean, single-step process.

Proof, not promises

Every number here follows one rule: no figure is asserted without its confidence interval attached. Where a bound is empirical, we say so. Where two measurements come from different populations, we say that too — and we do not combine them into a single flattering headline.

ChaserBench

A public, reproducible benchmark of 30 verifiable tasks (10 trivial, 10 medium, 10 complex), run as two matched arms: the Chaser cascade versus direct Sonnet. Each task is played by both arms, so the delta is measured on the same task rather than on two different populations.

  • Total cost: $0.1013 (direct Sonnet) vs. $0.0433 (Chaser)
  • 57% cost reduction at matched task, statistically proven
  • Empirical-Bernstein lower bound of the gain: 0.134, above 0
  • Success rate: 30/30 (direct Sonnet) vs. 29/30 (Chaser)
  • Median latency: 13.1s (direct Sonnet) vs. 11.8s (Chaser)
  • Quality gap: anytime-valid interval containing 0 → quality preserved
  • Corpus frozen and bound by a SHA-256 fingerprint

Raw machine-readable data: /bench/index.json · full benchmark page

AI-Scientist-v2 report (July 19, 2026)

An unmodified fork of AI-Scientist-v2 (SakanaAI) run through an OpenAI-compatible facade, integrated solely via OPENAI_BASE_URL — zero patches to the fork.

  • Session S1: $0.61 vs. $0.66 GPT-4o baseline → −7.2%
  • Session S3: $0.0612 vs. $0.1288 → −52.5%

These two figures measure different populations and do not add up. Each claim carries three independent signatures: integrity (Merkle RFC 6962 + Ed25519), execution (attested replay) and validity (adversarial Skeptic review).

Read the full report (FR)

All raw data behind these figures is public and independently verifiable. The hypotheses, protocols and reviews cited in the AI-Scientist report are AI-generated — that report states so explicitly.

Pricing

A one-time purchase. No extra subscription: Chaser is a local product you install once, with no recurring cost and no dependency on a third-party service.

17 € Student / Open-Source
  • All Bundle features
  • Up to 150 engine orchestrations per month
  • Handoff, fresh session, Cockpit and compressor included
  • Requires student or open-source project proof
47 €67 € Simple
  • Simple-level orchestrator
  • Multi-model routing with fallback
  • JSON traces for every run
  • Step-by-step install guide
Most chosen 97 €147 € Full Bundle — levels 1 + 2 + 3
  • All three orchestration levels
  • Automated handoff + long-term memory
  • Cascade, learned router, deterministic recipes
  • Output compressor + local Cockpit
  • Batch API, prompt caching, hard budget cap
from 497 € Enterprise
  • Team & production deployment
  • CI/CD integrations (GitHub Actions, GitLab)
  • Setup assistance
  • Priority support

Launch pricing. Chaser Check — the diagnostic installer — is free. The full product (routing engine, Shield, memory, Cockpit) unlocks after purchase with a personal, named license key. Runs on Windows 10 and 11; a macOS version is in preparation.

Frequently asked questions

What happens to my data?

Everything stays on your machine. Chaser doesn't send anything to a third-party server — the only network calls are the ones you already make to the Anthropic API. Local memory is human-readable and can be inspected or deleted at any time from the Cockpit.

Can I uninstall it cleanly if it's not for me?

Yes. Chaser is reversible in a single command, which removes the hooks and restores your previous configuration. It also uninstalls from the standard Windows "Apps & features" panel.

What does the free version actually do?

Chaser Check installs missing prerequisites (Python, Node.js, Git, Claude Code) and runs a read-only local diagnostic showing what Chaser could lighten — for example how many MCP tool schemas are inflating your system prompt. It doesn't include the routing engine, Shield or memory features; those require a license key.

What's the difference between my API bill and my subscription quota?

They're two separate wallets. Your API key is billed per token used — routing, caching and the cascade aim to lower that bill. Your Claude Code subscription has its own usage quota, which session recycling and output compression help you spend more slowly, independently of API cost.

What if Anthropic changes its models or pricing?

The routing, cascade and caching logic doesn't depend on today's specific prices — it works as long as a cost or capability gap exists between models. If Anthropic changes its lineup, the routing rules adapt; only the absolute figures in the traces would shift.

Verify integrity before running

The downloaded Chaser-Check.exe must have exactly this SHA-256 fingerprint:

1d1f84d0193737a05bbe2cded0a542a52e677c13b74036ccd863b460558841e4

On Windows, open PowerShell and paste: Get-FileHash "$HOME\Downloads\Chaser-Check.exe" -Algorithm SHA256 — the fingerprint must match. You can also check it on VirusTotal.

Publisher: Ken Caroly · 100% local — no data sent · reversible in one command