#memory

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

A modern background job engine for .NET, with reliable execution and real-time visibility.

Terminal coding agent with durable memory, hash-gated skill trust and a 61-task eval harness. Works with any OpenAI-compatible backend (GLM / DeepSeek / Qwen / Ollama).

the trust layer for agent memory

Semantic memory for AI agents — local-first MCP server with hybrid search, governance, and consolidation

The intentional memory layer for your AI agents.

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

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

Your AI chats Synced! 100% Free! Claude, ChatGPT, Gemini, Grok..! 1-click install, create your local Vault or make a fully featured USB Hub. No Ads. No E-Mail. No Trackers. No BS. Fully encrypted.

An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay

Your backlog is your agent's memory

Agentic engineering supersystem — one CLI to run the full /mavis-ship chain. Bundles 38 curated integrations + 1890 skills + the v2.7.1 arsenal (orchestrate.py + catalog.py + autopilot + mavis-ship-uni + big-boss persona). MIT.

A collection of open source Rust crates from iqlusion

Providing unified trait abstractions for AI models

Опис репозиторію не опубліковано.

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

MCP server for pūrmemo — AI conversation memory that works everywhere. Save and recall conversations across Claude Desktop, Cursor, and other MCP-compatible platforms.

The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.

rusty_alloc is a pure-Rust, memory safe alternative to mimalloc. Cross platform combability across x86-64 linux and windows, aarch64, wasm, and RSIC-V for ESP architecture.

State-of-the-art static memory allocation for neural networks.

Yadgar (یادگار) — Persian for "memento, keepsake." A persistent memory engine for AI coding agents that survives sessions and /clears: it decays what you stop touching, promotes what recurs, filters recall to the git branch you're on, and pairs every memory with a curated wiki searched through the same ranking pipeline. Works with any MCP client.

Bitemporal memory for AI agents: deterministic contradiction resolution, provenance, and retrieval at any point in time.

Local, privacy-first RAG memory system for Claude Code

A blazing fast memoization library that is tiny but feature-rich.

A lightweight, high-performance AI/RAG workspace and autonomous agent framework implemented in Go. Inspired by the Leann RAG backend architecture

Typed building blocks for everything around your LLM call.

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

A fast and flexible allocator for no_std and WebAssembly

Loro enterprise agent harness for coding, governed data, and productivity work