| Filename | Latest commit message | Latest commit date |
|---|---|---|
2688e2b936
Some checks failed
wai cross-architecture byte-equality / windows-x86_64 (pull_request) Successful in 23s
wai cross-architecture byte-equality / linux-aarch64 (pull_request) Successful in 40s
joule-code conformance gate / Build + round-trip C1-C4 vectors (pull_request) Failing after 1m3s
WAI conformance / cargo-class corpora · windows (pull_request) Successful in 1m13s
WAI conformance / cargo-class corpora · linux-arm64 (pull_request) Successful in 1m8s
wai cross-architecture byte-equality / macos-arm64 (reference) (pull_request) Successful in 1m57s
WAI conformance / cross-arch byte-equality · windows (pull_request) Successful in 23s
jouleclaw public surface must stay documented / Public-surface audit (jouleclaw-rs) (pull_request) Successful in 58s
no-vanity-metrics / Scan committed Markdown for vanity metrics (pull_request) Successful in 3s
standards workspaces build + test / jcp-rs (pull_request) Failing after 12s
WAI conformance / cross-arch byte-equality · linux-arm64 (pull_request) Successful in 39s
standards workspaces build + test / sandbox-rs (pull_request) Successful in 2m1s
wai cross-architecture byte-equality / linux-x86_64 (pull_request) Has been cancelled
WAI conformance / cargo-class corpora · linux (pull_request) Has been cancelled
WAI conformance / cross-arch byte-equality · linux (pull_request) Has been cancelled
WAI conformance / cross-arch byte-equality · macos (pull_request) Has been cancelled
WAI neural decoders end-to-end / synthetic fixtures → Rust decode → reference (±4) (pull_request) Has been cancelled
WAI conformance / cargo-class corpora · macos (pull_request) Has been cancelled
standards workspaces build + test / smart-byte-rs (pull_request) Has been cancelled
Lockfiles only — newest versions WITHIN the semver ranges the manifests already declare. No manifest constraint was widened by this commit. That distinction is load-bearing here. `cargo upgrade`, which rewrites manifests to the latest major, is precisely what killed smart-byte: rand was pinned to "0.10" against source written for 0.8, and the crypto stack it sits on (ed25519-dalek, curve25519-dalek, bls12_381, bulletproofs) all require rand_core 0.6 — so 0.8 is a ceiling those crates impose, not a preference. Moving past it means waiting for that ecosystem or migrating 41 call sites of cryptographic code, and neither belongs in a routine update. Largest moves: smart-byte 207 packages, openpay 189, jouleclaw 182, eoc 164. Verified on 1.98.0 with the updated lockfiles — 12 workspaces green: smart-byte 616 openpay 1935 joule-code 278 jcp 258 map 220 sandbox 186 aac 89 joulecontract 82 arl 58 sense 38 proof 31 joulehook 24 One pre-existing failure is deliberately NOT addressed here: jouledesk's `the_joule_budget_is_enforced_across_tags` seals two decisions where the budget permits one. It fails identically on the original lockfile, so it is not a dependency problem — it is a budget-enforcement defect in the Joule Desk standard, and a ceiling that seals a receipt for work it refused deserves its own fix and its own commit rather than burial in a dependency sweep. Co-Authored-By: Claude Opus 4.8 <[email protected]> |
||
| .. | ||
| conformance/v1 | ||
| jouleclaw-rs | ||
| vocab | ||
| LICENSE | ||
| 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
spec/LICENSE)