Executable cognitive architecture: validated graph context, deterministic cache, bounded JEV routing and evidence-gated model collaboration.
Quick read
Latest capture 2026-10-17 04:01
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
24 observed captures since 2026-09-24. Observed captures are shown by default.
Stars from first capture +3
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
A compatibility-first cognitive architecture for deterministic routing, evidence-aware traces, and reusable expert skills.
Deterministic-first cognitive orchestration with bounded TypeSafe JEV supervision, evidence-aware escalation, and privacy-minimizing telemetry.
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
Proof-carrying adaptive Luna-first cognitive routing for Promptothon 2026
A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
