爱憎 — preference memory for AI agents: extract, decay, and recall user likes and dislikes

Intelligent context management for long-session AI agents. Solves U-shaped attention curve and context decay problems with four-level memory hierarchy.

Thermodynamic memory for OpenClaw agents. Context Engine with constructive assembly and overflow prevention. SIU v2 pipeline (SIVU/SICU/SILU), Apache AGE knowledge graph, reactive triggers, multi-signal recall, interaction-based decay, local-first archite

Pure, zero-dependency P&C loss reserving engine for TypeScript: triangles, chain ladder, Mack, Bornhuetter-Ferguson, Benktander, Cape Cod (Gluck decay), Munich chain ladder, Clark growth curves, frequency-severity, Berquist-Sherman, ULAE, discounting, tai

nbake is a gentle and opinionated devops configuration tool for ubuntu+nodejs environments, that 'bakes' an environment - helping make configuration robust, reproducible and ephemeral. It prevents decay of an environment.

JavaScript client for the Entropy API — a living data ecosystem where memories decay when unobserved.

Episodic memory with decay, semantic search, and consolidation

ZenBrain's open-source memory algorithm library: 10 core algorithms (FSRS spaced repetition, Hebbian learning, Ebbinghaus decay, emotional tagging, sleep consolidation, Bayesian confidence, ...) + 10 advanced research modules (vmPFC-FSRS, two-factor Hebbi

Open-source CLI for PR regression-risk, blast-radius, and code-decay analysis

Cognitive infrastructure for AI agents. Beliefs with confidence and decay, governance enforcement, self-healing knowledge, vector search. SQLite-powered, zero-config.

Persistent memory MCP server with typed memories, decay scoring, and token-aware context injection

Memory infrastructure library — store, version, search, and decay knowledge over time

A drag-and-drop-enabled, responsive, envelope graph that allows to shape a wave with attack, decay, sustain and release

Mind Map — a memory consolidation / context-handoff MCP server. Capture context from any AI tool, resume it anywhere, and let it decay gracefully.

Cognitive science-based AI memory framework — Weibull decay, triple-path retrieval, multi-backend storage

Repository health & decay monitor — scans a codebase for committed secrets, vulnerable/abandoned dependencies, dead code, stale branches, aging TODOs and more, then scores it A–F. Emits terminal, JSON, Markdown or SARIF.

Tells your AI when the ecosystem shifts under your repo — watches dependencies for deprecations, quiet decay, and breaking majors, pushed into agent context via MCP

Kernloop Layer 2 — the toolsmith faculty (spec §5.6). Forge with mechanical birth requirements, the ratified Docker sandbox profile, the workshop/* namespace with its 12-tool cap, and the workshop authority ladder (suggest → advisory → enforce) with decay

Standalone, read-only dashboard for compatible `memory-decay` SQLite databases.

Deterministic memory dynamics for Aletheia: decay, promotion, and conflict revisits.