Plugins

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

Automatic conversation distillation: background subagent reflection + skill create/update.

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Self-evolving agent framework on DeepSeek Harness (dsh): 40 Cordis plugins and 4 presets covering memory, reflection, gates, metrics and an auditable evolution loop. Not a one-command install. Clone the repo and run install/install.sh --profile=web (needs bash, Node 20+, python3, DSH 0.1.7-rc.1 or newer with an initialized profile), then restart.

Distills session work into background observations and reflections to preserve context across compaction.

Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.

Project-scoped cross-session memory: PROJECT.md snapshot injected into the first user message, a memory_remember tool, and auto-reflection after ReAct tasks; each project keeps its own memory file.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

A reflection layer for DSH sessions that slowly rewrites a 3-7 entry worldview across value, preference and habit layers, tracks spirit, health and account balance, ingests Bilibili/Douyin videos, and keeps an auditable growth archive. Video intake is optional and needs site cookies; Douyin parsing also needs Edge/Chrome and yt-dlp.

Distills long sessions into background observations and reflections, injects them as a system-prompt section, and renders compaction summaries from prepared memory; includes a Settings page and source-backed recall.

Permanent memory plugin for DSH with vector search, LLM reflection, and knowledge pages.