Sessions & Messages

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)

Unlimited memory for OpenClaw

Gives dsh agents persistent cross-session memory: auto-recalls relevant user/task context before each turn and writes back lessons after each turn, evolving memory via schema learning and skill distillation

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.

Task-aware reasoning-mode router for DSH: classifies first real user message (build/fix/ambiguous), injects matching persona + band-gated tool surface, progressive tool disclosure, dev_router_status/mode/subagent commands

在 Web 输入区提供可组合的工作状态/思考策略/质量门禁/自进化控件；隔离式学习请求生成待人工审阅规则提议并写入全局 learned instructions；支持对抗性审查、验收审查与官方 plan-mode 委托

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

DeepSeek Harness plugin for previewable cross-preset session migration. Fixed-schema handoffs preserve state, source-model intent, and unresolved images; the original session stays untouched.

Cross-session long-term memory infrastructure for DSH agents: memory write/retrieve, continuous learning, auditable trust ('智能论 v3.2').

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

Delete one complete turn from a DeepSeek Harness session without deleting the session

消息撤回、重编辑插件：最无感的撤回/重编辑体验，设置丰富，兼容性强，轻量 UI 框架。

Cross-session seven-layer memory (soul/user/project/fact/lesson/topic/rules) with BM25 retrieval and per-window dream consolidation for DSH agents

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

A macOS-only native account-pool and provider plugin for DeepSeek Harness.

A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.

DSH 跨会话记忆插件：本地优先（SQLite）自动捕获对话与工具结果、L0-L5 分层存储、事件/元素卡片+知识图谱+时间线 UI、BM25+结构化混合检索、证据门控防无据作答、来源追溯

Claude Code-style in-place /rewind for DSH web profile: cut conversation back to any earlier user message, optional workspace-file restore from disk-persisted before-backups, per-message button + candidate picker UI

Adds WorkBuddy models to the DSH model picker with zero configuration across Web/Desktop/TUI; settings card shows account info and remaining credits.

【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

Archive sessions from sidebar, browse/manage in Settings->Archived, restore single/all, permanent delete with double-confirm.

Export the append-only session log as human-readable Markdown or HTML, grouped by trajectory source.

基于事件溯源的消息编辑/重生成/重试/版本时间线：从回合边界分支创建新会话版本，undo/redo 与 Timeline 标签页。

Branch from any answer and keep branching at any depth. Recursively isolated follow-ups that leave the main DSH task untouched.

Share your conversations with one click.

Adds a recall (撤回) button per user message: snapshot workspace into a shadow git repo at send time, restore files and fork the session back to pre-message state; settings UI for exclusions.

Delete DeepSeek Harness sessions from the UI: header danger button + sidebar session-row menu item (no conversation jump), risk-consent dialog with session name/id, stops running agents first, in-place list refresh without page reload. Works in web and the desktop client.

Mnemosyne OS 7.0.0 — zero-dependency, local-first AI memory system (MCP / API / CLI / Python). MIT.

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.