Encrypted memory for Claude, on a server you deploy to your own Cloudflare account.

The self-improving context engine for coding agents.

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.

🐋 DSH 鱼的记忆：给会话一份会淡忘的长期记忆，每条都带时间。名字里的「鱼」来自 DeepSeek 的鲸鱼。

DeepSeek Harness 记忆系统(单包单入口):JSONL 存储 + 本地向量检索(BGE-M3)+ 五个模型工具 + 自动召回注入 + 管理面板。

给 DeepSeek Harness 的本地记忆层：养大肥鱼的可以下载来玩，经过测试下载之后比单纯用RAG和外部记忆库更有人情味更自然了。

The self-improving context engine for coding agents.

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.

Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.

Enables keyless translation between languages using machine translation and community translation memory, with automatic source-language detection, match-quality scores, and alternate candidate translations.

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.

Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.

Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect.

Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

Chipp: a project's memory, circles, and scheduled tasks

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.