| Filename | Latest commit message | Latest commit date |
|---|---|---|
|
All checks were successful
energy meters on real hardware / RAPL and NVML on jetson-hub (pull_request) Successful in 48s
lockfiles / every Cargo.lock is current (pull_request) Successful in 43s
standards workspaces build + test / which workspaces this change touches (pull_request) Successful in 18s
tests in CI / every test file is run by a job or listed with its reason (pull_request) Successful in 10s
wai-quantum WebGPU member / does this change touch it (pull_request) Successful in 10s
workflow hygiene / every workflow supersedes its own queue (pull_request) Successful in 10s
standards workspaces build + test / jouleclaw-rs (-nodebug, jouleclaw/jouleclaw-rs, -p jouleclaw-energy --features rapl,nvml, jouleclaw-rs, linux-arm64, -C target-feature=+fp16) (pull_request) Successful in 3m40s
jouleclaw public surface must stay documented / Public-surface audit (jouleclaw-rs) (pull_request) Successful in 1m4s
spec citations resolve / Code cites no section its SPEC lacks (pull_request) Successful in 4s
wai-quantum WebGPU member / member · discrete GPU, Vulkan (jetson-hub) (pull_request) Successful in 10m26s
standards workspaces build + test / aac-rs (aac-conformance, aac/aac-rs, aac-rs, linux-arm64) (pull_request) Successful in 3m13s
standards workspaces build + test / joule-code-rs (joule-code/joule-code-rs, joule-code-rs, linux-arm64, true) (pull_request) Successful in 1m30s
standards workspaces build + test / joulecontract-rs (joulecontract/joulecontract-rs, joulecontract-rs, linux-arm64, true) (pull_request) Successful in 58s
standards workspaces build + test / map-rs (map-conformance, map/map-rs, map-rs, linux-arm64) (pull_request) Successful in 1m20s
standards workspaces build + test / mesh-rs (mesh/mesh-rs, -p mesh-engine-gguf -p mesh-openai --features mesh-engine-gguf/gguf,mesh-openai/server, mesh-rs, linux-arm64) (pull_request) Successful in 55s
standards workspaces build + test / openpay (openpay, openpay, linux-arm64) (pull_request) Successful in 2m53s
standards workspaces build + test / macOS energy backends (pull_request) Successful in 5m32s
standards workspaces build + test / jouledesk-rs (jouledesk/jouledesk-rs, jouledesk-rs, macos) (pull_request) Successful in 52s
wai-quantum WebGPU member / member · Metal (macos) (pull_request) Successful in 2m11s
wai-quantum WebGPU member / member · browser WebGPU (macos) (pull_request) Successful in 1m28s
standards workspaces build + test / arl-rs (arl/arl-rs, arl-rs, linux) (pull_request) Successful in 1m15s
standards workspaces build + test / jcp-rs (jcp-conformance, jcp/jcp-rs, -p jcp-energy --features nvml, jcp-rs, linux) (pull_request) Successful in 1m50s
standards workspaces build + test / eoc-rs (eoc/eoc-rs, -p eoc-meter --features cuda, eoc-rs, linux) (pull_request) Successful in 2m9s
standards workspaces build + test / joule-ui-rs (joule-ui/joule-ui-rs, joule-ui-rs, linux) (pull_request) Successful in 1m10s
standards workspaces build + test / joulehook-rs (joulehook/joulehook-rs, joulehook-rs, linux) (pull_request) Successful in 1m12s
standards workspaces build + test / proof-rs (proof-conformance, proof/proof-rs, proof-rs, linux, true) (pull_request) Successful in 1m41s
standards workspaces build + test / sandbox-rs (sandbox-conformance, sandbox/sandbox-rs, sandbox-rs, linux) (pull_request) Successful in 2m26s
standards workspaces build + test / sense-rs (sense/sense-rs, sense-rs, linux) (pull_request) Successful in 1m8s
wai-quantum WebGPU member / shader checks · browser build · wasip2 inertness · MSRV (pull_request) Successful in 3m24s
standards workspaces build + test / smart-byte-rs (smart-byte/smart-byte-rs, smart-byte-rs, linux) (pull_request) Successful in 4m1s
wai-quantum WebGPU member / member · software Vulkan (linux) (pull_request) Successful in 2m5s
wai-quantum WebGPU member / member · DX12 and Vulkan (cbio-windows) (pull_request) Successful in 12m0s
EnergyLedger summed microjoules with no grade. Its `costs` defaults are
fixed figures, and the docs called one "measured". So a total built from
estimates looked the same as one built from readings, in the serializable
snapshot too. Now:
- `record` and `record_batch` take the deposit's `Provenance`. The ledger
keeps the weakest grade it was given (one `fetch_min`, still lock-free).
`provenance()`, `LedgerSnapshot::provenance` and the summary report that
grade; an empty ledger has none, and `reset` clears it. The order of the
grades is pinned to `span::weaker` by a test.
- The `costs` docs say what the figures are: defaults carried over from
another codebase's measurements, calibrated on no host that uses them, so
a deposit computed from one is `Estimator`. "measured" is gone.
- The orderings the defaults must keep are checked when the crate builds
(`const _: () = { assert!(..) }`), not in a test of constants that clippy
flagged as `assertions_on_constants`.
CI: the macOS energy job now runs clippy, with `-D warnings`, on the eight
crates whose meter code compiles only on macOS: jcp-energy, jcp-gateway,
proof-cascade, proof-solvers, eoc-meter, jouleclaw-energy (ioreport),
sandbox-meter and sandbox-proof. No Linux job lints that code, which is how
the lints fixed in #244 went unseen. All eight pass today.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
|
||
| .. | ||
| conformance/v1 | ||
| jouleclaw-rs | ||
| scales | ||
| vocab | ||
| LICENSE | ||
| LICENSE-SPEC | ||
| README.md | ||
| ROADMAP.md | ||
| SPEC.md | ||
JouleClaw — Energy-Optimized AI Runtime
The substrate for AI that costs Joules, not tokens.
Capability per Joule, not capability per parameter.
What JouleClaw is
JouleClaw is a pure-Rust, omni-modal AI runtime + harness + agentic layer governed by Transaction Science as an open standard (5th in the open-standards quartet, alongside OpenPay, Smart Byte, EOC, and WAI).
Every operation JouleClaw performs walks an explicit energy-tiered cascade, top to bottom, stopping at the first stage that closes the query:
| Tier | Name | Cost class | What runs here |
|---|---|---|---|
| L0 | Cache | picojoules | Content-addressed cache hits |
| L1 | Lawful | nanojoules | Deterministic, pre-compiled primitive (text/code only) |
| L2 | Embed | sub-millijoules | Matryoshka embeddings + nearest-neighbor + hybrid search |
| L3 | Model | joules | Local SSM / ternary / multimodal / diffusion / etc. |
| L4 | Wire | tens of joules | Remote frontier RPC (escape hatch only) |
L1 (Lawful) is only meaningful for text and code modalities. For image, audio, video and 3D generation, the cascade collapses to L0 / L2 / L3 / L4 — the energy savings come from caching plus dispatch to the cheapest model that meets the quality bar.
Why JouleClaw exists
The mainstream "agentic AI" ecosystem treats inference as the entry point. Every state shift, every tool call, every routing decision runs through a 70-billion-parameter stochastic engine, burning kilojoules to do work that deterministic compute or a hot cache could resolve for microjoules.
JouleClaw inverts the default. Inference is the last resort, not the first. Frozen model weights are less trustworthy than current world state; fresh, provenance-stamped retrieval beats synthesis from training cuts. Every operation is metered in microjoules where the hardware permits it, and in millijoules where it doesn't — the spec is honest about the floor on every platform.
The thermodynamic circuit breaker is the safety mechanism. Set an energy budget; when measured consumption exceeds the budget, the breaker trips and the operation halts. Hallucination loops cannot survive an honest joule ledger.
What's here
| Path | Contents |
|---|---|
SPEC.md |
JouleClaw v1 spec — cascade tiers, energy contract, receipt |
CHARTER.md |
Stewardship pattern (shared across open-standards) |
jouleclaw-rs/ |
Apache-2.0 Rust reference implementation |
spec/ |
Tier specifications, energy provenance, receipt format |
conformance/v1/ |
Signed wire vectors for cross-implementation verification |
Reference implementation
jouleclaw-rs/ is the Apache-2.0 reference implementation in Rust. It
runs on Apple Silicon (M3/M4/M5 with UMA + Metal 4 Tensor APIs), AMD Strix
Halo / Ryzen AI Max, Intel Lunar Lake, NVIDIA Jetson, and discrete
NVIDIA / AMD GPUs.
It is omni-modal: text, code, vision, audio, video, image diffusion, 3D Gaussian splatting, and cross-modal fusion all dispatch through the same energy-tiered cascade.
The MCP tool surface is a JCP consumer: jouleclaw-jcp wraps any
jouleclaw-mcp metered tool so every dispatch is decided by the JCP runtime
against a signed, metered Grant before a byte reaches the tool — the tool's
identity is the content-addressed resource, the call's energy estimate is
debited from the grant's joule budget, and every decision (allow and deny
alike) seals as a JCR-1 receipt. An injected instruction can name an ungranted
tool; it cannot make the gate dispatch it.
Status
v0.1.0 reference implementation in active development. The spec is draft status. Cross-implementation conformance vectors will land with v1.0.0.
License
- Code: Apache-2.0 (see
LICENSE) - Spec text: CC-BY-4.0 (see
LICENSE-SPEC)