#memory

Self-hosted AI memory engine - Ebbinghaus forgetting-curve decay, interaction-aware reinforcement, and conscious thought synthesis. Local SQLite + sentence-transformers embeddings.

Local-first, auditable memory for Codex, Claude Code, and MCP-compatible AI agents.

End-to-end encrypted memory for AI agents — portable, yours forever.

SKCapstone — The sovereign agent framework. CapAuth backbone. Cloud 9 trust. SKMemory persistence. Same agent, same bond, same context — everywhere. Runs from ~/.

A memory efficient string type that can store up to 24* bytes on the stack

Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.

A second brain for Claude Code: project memory, real token & cost accounting, local semantic recall, and active guardrails.

Shared memory across your team and your AI agents — with judgment about what's worth keeping.

A multi-driver caching library for Go that makes swapping cache backends trivial without changing application code.

Persistent memory for pi — learns corrections, preferences, and patterns from sessions

No repository description published.

Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.

MCP server for persistent AI memory — give any AI assistant long-term recall. Works with Claude, Kiro, Cursor, Windsurf.

Open protocol and reference node where humans, their AI agents, and local LLMs share apps, knowledge, and capabilities. Self-hosted, federated, MIT.

An easy tool to monitor the performance of your R3F application.

No repository description published.

A living local memory layer for your AI tools.

Read memory from another process

Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

No repository description published.

Persistent, queryable memory for AI agents with semantic recall, layered storage, snapshots, and multi-agent scoping

Database Abstraction Layer provides a highly flexible and extensible storage interface that provides a unified way to interact with different storage backends.

Memory Health Check for Laravel Health and Oh Dear & Monitoring Service

Tellstone is a high-performance in-memory database and drop-in replacement for Redis; Join https://discord.gg/kEf78DUFX

Makes AI stateful across sessions. Workflow: chat → idea → design → reqs → plan → do_step(s) → done, with fresh scoped context, staleness detection, and human approval at every phase. Roadmap & history of shipped features.

Spor — a shared memory substrate for teams and agents. Decisions, their reasons, and the traces they leave.

SQLite Wasm compiled with automatically initialized sqlite-sync and sqlite-vector extensions. Conveniently packaged as an ES Module for effortless integration.

No repository description published.