open-standards/jouleclaw
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Claude 19904251b7
All checks were successful
jouleclaw public surface must stay documented / Public-surface audit (jouleclaw-rs) (pull_request) Successful in 59s
standards workspaces build + test / which workspaces this change touches (pull_request) Successful in 5s
repository checks / lockfiles, tests in CI, workflow hygiene, spec and section references, public text (pull_request) Successful in 37s
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 3m18s
standards workspaces build + test / joulecontract-rs (joulecontract/joulecontract-rs, joulecontract-rs, linux-arm64, true) (pull_request) Successful in 1m11s
standards workspaces build + test / arl-rs (arl/arl-rs, arl-rs, linux) (pull_request) Successful in 1m13s
standards workspaces build + test / aac-rs (aac-conformance, aac/aac-rs, aac-rs, linux-arm64) (pull_request) Successful in 4m18s
standards workspaces build + test / map-rs (map-conformance, map/map-rs, map-rs, linux-arm64) (pull_request) Successful in 1m19s
standards workspaces build + test / eoc-rs (eoc/eoc-rs, -p eoc-meter --features cuda, eoc-rs, linux) (pull_request) Successful in 2m10s
standards workspaces build + test / jcp-rs (jcp-conformance, jcp/jcp-rs, -p jcp-energy --features nvml, jcp-rs, linux) (pull_request) Successful in 2m2s
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 1m27s
standards workspaces build + test / joule-ui-rs (joule-ui/joule-ui-rs, joule-ui-rs, linux) (pull_request) Successful in 1m11s
standards workspaces build + test / joulehook-rs (joulehook/joulehook-rs, joulehook-rs, linux) (pull_request) Successful in 1m14s
standards workspaces build + test / joule-code-rs (joule-code/joule-code-rs, joule-code-rs, linux-arm64, true) (pull_request) Successful in 5m6s
standards workspaces build + test / pool-rs (pool/pool-rs, pool-rs, linux) (pull_request) Successful in 1m7s
standards workspaces build + test / proof-rs (proof-conformance, proof/proof-rs, proof-rs, linux, true) (pull_request) Successful in 1m50s
standards workspaces build + test / sense-rs (sense/sense-rs, sense-rs, linux) (pull_request) Successful in 1m11s
standards workspaces build + test / sandbox-rs (sandbox-conformance, sandbox/sandbox-rs, sandbox-rs, linux) (pull_request) Successful in 2m25s
standards workspaces build + test / openpay (openpay, openpay, linux-arm64) (pull_request) Successful in 8m30s
standards workspaces build + test / smart-byte-rs (smart-byte/smart-byte-rs, smart-byte-rs, linux) (pull_request) Successful in 4m27s
standards workspaces build + test / macOS energy backends (pull_request) Successful in 8m25s
standards workspaces build + test / jouledesk-rs (jouledesk/jouledesk-rs, jouledesk-rs, macos) (pull_request) Successful in 2m52s
jouleclaw-backend-apple: 0 warnings, and the gate covers both configurations
10 -> 0, and the `-D warnings` step now lints loader-gguf under
`rayon fabric-meter` as well as on default, plus backend-apple on its
own. That closes the per-configuration lint hole #373 opened and #414
halved.

The last ten, all in mps_matmul.rs:

- `struct PipelineCell` with its `unsafe impl Send`/`Sync` was never
  constructed and mentioned nowhere else -- scaffolding for a OnceLock
  wrapper the pipelines ended up doing directly. Removed, and the space
  reused for a `KeepAlive` alias, which is what the two `type_complexity`
  warnings wanted: the inline form is three generic layers deep and
  appeared twice.
- `DeviceKvCache` had a public `len` and no `is_empty`.
- three `let qk_pipe = qk_pipe;` no-op rebindings from a refactor.
- `too_many_arguments` and `needless_range_loop` allowed crate-wide, the
  same two decisions omni and loader-gguf already record and for the same
  reasons: a GPU dispatch signature is its kernel's parameter list, and
  these kernels walk several buffers at one index.

The comment this replaces in standards-build.yml claimed the fabric-meter
configuration could not be gated because backend-apple's warnings "are
unused in THAT configuration and needed in others, so they want cfg work
rather than deletion". Measuring the crate directly refuted both halves:
it has no `[features]` at all, so there is one configuration, and the
count was 84 rather than the 43 that leaked through loader-gguf's lint.

Verified: all ten lint specs in the step pass, 37 backend-apple tests
(32 pass, 5 ignored), 343 loader-gguf tests, 77 omni tests.

Co-Authored-By: Claude Opus 5 <[email protected]>
2026-10-22 06:58:23 -04:00
..
conformance/v1 jouleclaw SPEC.md: normative §§8-12 for waves 12-21 2026-06-02 10:42:25 -04:00
jouleclaw-rs jouleclaw-backend-apple: 0 warnings, and the gate covers both configurations 2026-10-22 06:58:23 -04:00
scales compliance: publish the EU draft PUE bands as a sourced data pack, not as code 2026-09-06 06:24:25 -04:00
vocab jouleclaw: wave-24 — contract + handoff + mission + value report 2026-06-03 02:35:34 -04:00
LICENSE jouleclaw: standard skeleton + Phase 1 foundation crates 2026-05-26 09:55:11 -04:00
LICENSE-SPEC licences: ship the Apache-2.0 text the code already declares 2026-10-09 17:22:32 -04:00
README.md licences: ship the Apache-2.0 text the code already declares 2026-10-09 17:22:32 -04:00
ROADMAP.md docs: strip vanity metrics from README + ROADMAP 2026-06-02 07:30:50 -04:00
SPEC.md energy meters: a GPU counter reading low is refuted in sandbox-meter, eoc-meter and jcp-energy too 2026-10-20 04:15:36 -04:00

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