15 projects
buto
Reserved name held by Cruxia-Labs. Contains no implementation; installing it does nothing.
campanile
Replay a repository's git history offline and report its line-custody structure — which author strings held which file classes, and when that shifted.
sagrada-tracker
Reserved name held by Cruxia-Labs. Contains no implementation; installing it does nothing.
sagrada-preflight
Reserved name held by Cruxia-Labs. Contains no implementation; installing it does nothing.
sagrada-mcp
Sagrada MCP server: track and verify reasoning state for AI systems via Model Context Protocol
er1-verify
ER1 — reference offline verifier for Epistemic Receipts (constraint-state receipts)
sagrada-engine
Deterministic belief-revision operator for AI agents — hash-chained, replayable, verifiable
sagrada-distill
Distill a repository's decision record into a verifiable .crux artifact (release-candidate placeholder; first stable release imminent)
sagrada-linter
Catch zombie beliefs — dead rules that crept back into your .cursorrules / CLAUDE.md / AGENTS.md — with a verifiable receipt.
chain-receipt-sdk
Chain-Receipt SDK — emit, verify, replay, and chain Receipts (v1.0.0) from LangChain, LlamaIndex, LangGraph, Pydantic AI, DSPy, or any Python callable.
agm-r
AGM-R: theorem-minimum reference implementation of AGM belief-revision primitives (T-I1, T-I2, T-M1).
chain-determinism-harness
Measure chain-determinism (per-trace structural consistency across replays) for any OpenAI-compatible LLM endpoint.
chain-receipt-core
Reference implementation of the Chain-Receipt v1.0.0 spec — canonical JSON, SHA-256 receipt hash, Ed25519 signing, chain integrity, replay-attestation primitives.
epistemic-vectors
Epistemic Vectors — a provenance-native primitive for retrieval pipelines. Drop-in Epistemic Layer for LangChain, LlamaIndex, and Mem0.
cruxia-cv
Vendor-agnostic LLM agent measurement SDK (placeholder reservation; v0.1.0 in active development).
