AI/ML●●Solid
ÆTHERYA Core – deterministic action-governance kernel for LLM agents
Fail-closed policy layer blocks LLM tool calls before execution, no LLM in decision path.
Big BrainNiche Gem
RobertMihai
103mo ago
Back to browse
GitHub Repository
Deterministic proof-carrying decision core with replay verification, WAL, and fixed-point budget proofs
0 starsRust
Calybris Core, a deterministic audit engine for decisions in Rust
by emirhuseyininci·Jun 29, 2026·3 points·0 comments
AI Analysis
●●SolidNiche GemBig Brain
Deterministic replay kernel for decisions when you need to prove why something was rejected.
Strengths
- •Proof-carrying decisions with tamper-evident WAL is genuinely clever for compliance.
- •Domain-neutral primitive design avoids framework bloat — just the decision kernel.
- •Miri/Loom coverage and #![forbid(unsafe_code)] shows serious Rust hygiene.
Weaknesses
- •Zero stars, zero forks — too early to tell if this solves real pain.
- •Extremely niche audience — only matters if you're building auditable decision systems.
Category
Target Audience
Systems engineers building auditable fintech or LLM routing infrastructure
Similar To
OpenPolicyAgent · TeddyDB
Similar Projects
Productivity●Mid
Decision Audit – A deterministic decision engine for career pivots
Avoids LLM hallucination with deterministic scoring, but a pros/cons spreadsheet solves the same problem.
cosmok
214mo ago
AI/ML●●●Banger
DashClaw – intercept and audit AI agent decisions before they execute
Governance before execution solves the black-box agent problem observability tools ignore.
Zero to OneBig BrainBold Bet
ucsandman
223mo ago
Infrastructure●●Solid
ExoArmur – Deterministic governance runtime for autonomous systems
Verifiable decision replay for autonomous systems, but execution complexity limits adoption beyond safety-critical domains.
Big BrainNiche Gem
slucerodev
103mo ago
Security●●Solid
Qarapace – GCP IAM reviews with persistent decisions and audit trails
Persistent IAM review with audit trails beats one-shot scanners, but GCP-only limits reach.
Solve My ProblemNiche Gem
gjanvier
103mo ago
Developer Tools●●●Banger
Cruxible Core – Deterministic decision engine with receipts for agents
Auditable agent decisions via DAG receipts—unlike prompt-dependent LLMs, this proves reasoning.
Big BrainSolve My ProblemZero to One
rmalone1097
203mo ago