Whole Body Compute (body)
Cut agent token burn and latency with zero accuracy loss on SWE-bench Verified.
Whole Body Compute makes AI computing simpler, faster, and local: giving Claude Code, Cursor, Windsurf, Cline, Goose, and Antigravity a <3ms AST context shield, native macOS vision, and on-device memory right on your Mac (with cross-platform Blood-Brain Barrier & FinOps audit support on Linux).
Open-Core Spec (wholebodycompute.com/open-core) · Zero-Install Spend Audit (audit.py) · Commercial Platform (wholebodycompute.com) · Benchmarks (benchmarks/) · Architecture Wiki
Quickstart
# Option 1: 1-line installer (macOS & Linux)
curl -fsSL https://wholebodycompute.com/begin | sh
# Option 2: uv / pipx directly from GitHub
uv tool install git+https://github.com/wholebodycompute/whole-body-compute.git && body begin
# Option 3: Source checkout
git clone https://github.com/wholebodycompute/whole-body-compute.git
cd whole-body-compute
python3 -m venv .venv && source .venv/bin/activate && pip install -e .
body begin
Or run a read-only 30-day token spend audit across your local agent logs with zero installation:
curl -sSL https://wholebodycompute.com/audit.py | python3
What It Does
Cloud coding agents burn massive context windows re-ingesting full files, noisy test logs, and screenshots on every turn. Whole Body Compute (body) sits locally between your coding agent and macOS/Linux hardware, intercepting bloated reads and tool outputs in <3ms before they hit your cloud billing meter.
┌────────────────────────────────────────────────────────────────────────────────────────┐
│ WHOLE BODY COMPUTE (5 CORE ORGANS) │
├──────────────────────────┬──────────────────────────┬──────────────────────────────────┤
│ 01. THE HEART │ 02. THE BRAINSTEM │ 03. THE EYES & HANDS │
│ Thermal, Perfusion & CSI │ Local Metal, Router & KV │ Foveal AX DOM, Tactile & Vagus │
├──────────────────────────┼──────────────────────────┴──────────────────────────────────┤
│ 04. THE HIPPOCAMPUS │ 05. THE IMMUNE SYSTEM (BLOOD-BRAIN BARRIER) │
│ Memory WAL, Flush & REM │ Pre/Post Hooks, SensoryVector, <3ms AST Slicer & SecGate │
└──────────────────────────┴─────────────────────────────────────────────────────────────┘
| Capability | Standard Unshielded Cloud Agent | With Whole Body Compute (body) |
Measured Impact |
|---|---|---|---|
| Harness Wiring | Manual per-editor rules & scattered scripts | body begin auto-wires PreToolUse / PostToolUse hooks across Claude Code, Cursor, Antigravity, Windsurf, Cline & Goose |
60-second setup + 30-day FinOps receipt |
| File & Log Reads | Unbounded read_file (2,000+ lines) & raw pytest/cat dumps |
Blood-Brain Barrier (<3ms AST Symbol Slicer) + local Metal ReconScout |
Up to 98.7% token reduction on large reads |
| Desktop Vision | Full-screen PNG loops (7,650+ tokens/step) or heavy 24/7 video recorders |
Foveal Vision (AXUIElement DOM) + <50ms Tactile git/file delta sensor (<50MB RAM) |
96.9%–99.5% sensory token reduction |
| Session Hygiene | $O(N^2)$ turn accumulation until context degrades | Cognitive Sentry (body context) + StateCapsule Flush (body flush) [Pro] |
Zero-loss handoff in <30 steps |
| Pre-Egress Security | Cloud classifiers run after data leaves your machine | <1ms 23-vendor secret redaction, 1Password/Keychain blindfold, <2ms APFS CoW airlock & AST SecGate |
0 secret leaks · 0.0% ASR on AgentDojo |
Benchmarks (SWE-bench Verified & Princeton HAL)
Evaluated across 146 live unscripted agent sessions (including 100 official upstream princeton-nlp/SWE-bench_Verified runs across 10 Python organizations at untouched historical commits, graded strictly against held-out FAIL_TO_PASS + PASS_TO_PASS test patches):
| Evaluation Suite | Baseline (Unshielded) | + Whole Body Compute |
Key Empirical Result |
|---|---|---|---|
SWE-bench Verified (k=3, 60 Live Trials)Gemini 4 Carbon across 10 official orgs |
30/30 (100% Pass@1)10/10 Pass^3 · 203.08M ctx |
30/30 (100% Pass@1)10/10 Pass^3 · 137.23M ctx |
Zero accuracy loss (100% strict 3/3 consistency), -32.4% total context (-65.85M tokens), -25.6% billed input, -18.8% fewer turns |
SWE-bench Verified (Claude Code 2x2, 40 Runs)Claude Sonnet & Claude Haiku CLI |
Vanilla Sonnet: 9/10 ($4.00)Vanilla Haiku: 8/10 ($4.42) |
Sonnet + WBC: 10/10 ($3.89)Haiku + WBC: -36.1% ctx ($3.05) |
Sonnet + WBC solved 10/10 (100%) and cost -12.0% LESS than Vanilla Haiku ($3.89 vs. $4.42) while beating it by +20.0pp accuracy |
Multi-Track Live A/B (18 Sessions)SWE-bench + CORE-Bench Hard + OSWorld |
Haiku 4.5: 9/9 (100%)5.26M ctx · $1.60 · 312.9s |
Haiku 4.5 + WBC: 9/9 (100%)1.55M ctx · $0.51 · 190.5s |
-67.8% API spend (3.11x efficiency), -71.9% billed input, -39.1% faster wall-clock time |
Security & Reliability (AgentDojo + CyberSecEval 3) |
100.0% Attack Success (12/12) |
0.0% Attack Success (12/12 blocked) |
0.0% false-positive rate (6/6 benign passed), 0.102ms in-process gate overhead |
Full per-repository tables, 2x2 model matrices (Sonnet, Haiku, Gemini, GPT-OSS 120B), raw JSON telemetry receipts, and 1-command verification harnesses: benchmarks/README.md.
CLI Reference (body)
# Core Onboarding, Audit & Organ Primitives (Free Forever)
body begin # Wire Blood-Brain Barrier hooks & print 30-day FinOps ROI receipt
body audit-spend # Scan Claude Code, Cursor, Antigravity, Windsurf, Cline, Goose, Codex & Aider spend
body savings # Inspect live Blood-Brain Barrier token savings & active shield status
body report # 5-Pillar operational & FinOps scorecard (Session, 24h & 7d trends)
body doctor # Sub-second 5-organ health check (--exercise runs closed-loop reflex verification)
body heart # Thermal state, Unified RAM headroom & model perfusion status
body eyes # Live macOS AXUIElement Foveal DOM snapshot + on-demand Apple Vision OCR
body hands # Deterministic UI actuation (ax_act) & <50ms tactile git/file delta sensor
body immune # Blood-Brain Barrier audit log (--window 24h --tools --blocked), APFS CoW & SecGate
body daemon status # Manage portable macOS LaunchAgents (install / status / logs)
# Sovereign Context, Memory & Autonomous Consolidation [Pro / Team]
body license # Activate Pro/Team Polar key (--activate <KEY>) or inspect tier quota
body context # Context Saturation Index (CSI) & bloat attribution (--insights) [Pro]
body flush --auto # Grounded StateCapsule session handoff & metabolic noise purge [Pro]
body memory # Persistent Hippocampus SQLite WAL & FTS5 recall (--remember / --recall) [Pro]
body perfusion # Evict idle local Metal models (--evict) or pre-warm weights (--prewarm) [Pro]
body sleep # Nocturnal REM consolidation & Radix KV-Cache prefix digest [Pro]
Deep-dive component reference and glossary: docs/WIKI_AND_GLOSSARY.md.
License
Free forever for individual developers, researchers, and internal non-competing business use under the Open-Core Community License (LICENSE) and PATENTS.md - commercial resale, managed hosting, or embedding into competing IDEs, agent harnesses, gateways, or FinOps products requires a separate commercial license (hello@wholebodycompute.com).
1 maintainer
Metadata
1 maintainer
Release files for whole-body-compute 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| whole_body_compute-0.1.0.tar.gz | 1.0 MB | With provenance | Details for whole_body_compute-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| whole_body_compute-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for whole_body_compute-0.1.0-py3-none-any.whl |
Total release size: 2.0 MB
Release files / whole_body_compute-0.1.0.tar.gz
| Download URL | whole_body_compute-0.1.0.tar.gz |
|---|---|
| Size | 1.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
45c8b77c883dfd2f33c341b0daf7c58bc016a72896a3ff9aac959cb5a877c6d3
|
|
BLAKE2b-256 checksum How to use checksums |
038f92697767267c003ca0d07acefd4c485533d76ccbfcbb172a6c866e57379e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.
Transparency logRelease files / whole_body_compute-0.1.0-py3-none-any.whl
| Download URL | whole_body_compute-0.1.0-py3-none-any.whl |
|---|---|
| Size | 1.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c137a495c51fe8fcc70a50e389c2ff78443dd7270a71deae8cd78a80824b74fc
|
|
BLAKE2b-256 checksum How to use checksums |
8ab01a3cafebe8de25ff3220439258fba4c3b6e78bf8b935ecb99ad39b9bdc7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.
Transparency logSecurity for whole-body-compute 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for whole_body_compute-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
