Agents, Automation & Workflows

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

AgentTeams plugin for DeepSeek Harness

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

A DeepSeek Harness plugin for Context dashboard and command — showing what the model's context window is made of and how it evolves.

消息锚定的工作区文件回滚/恢复（基于持久化 Change Ledger）

A Skill-driven Harness/Loop Engineering Workflow Agent Plugin

在全新 Agent Session 中调度 coding 任务

DSH Web fourth-column (aside) panel for OpenBiliClaw plus 22 openbiliclaw_* agent tools bridging a local personalized content-recommendation backend.

Structured memory engine for DeepSeek Harness. Offline semantic search, entity-attribute-timeline, autoDream self-consolidation, and human-editable Markdown storage.

AGI long-term memory base: multi-agent spatiotemporal memory graph, self-evolving knowledge flywheel, self-cognition, and auditable trust guardrails.

OpenMAIC for DeepSeek Harness: classrooms, slides, interactive widgets, and Socratic teaching

A caring memory companion for DSH — three-layer auto memory, proactive calendar reminders, warm AI greetings, per-turn auto-consolidation, and inheritance of memories from other AI tools.

Condition-driven wakeup for DeepSeek Harness: durable file/command/http/process/webhook watches that wake the agent, with dock, sidebar branch, and a global dashboard.

Configurable subagent profile system: single subagent tool + profile parameter, Web UI settings, real-time progress, subagent tree tab.

Adds a `shell` tool that unifies PowerShell / Git Bash / WSL command execution on Windows via ctx.subprocess; coexists with sandboxed default pwsh (process-tree kill, SIGTERM->grace->SIGKILL, output spill files).

Persistent multi-model agent squads for DeepSeek Harness — reusable teams, per-agent model/tool policies, and ordinary-chat collaboration.

Agent-agnostic workflow skill for maintaining Obsidian knowledge bases

Self-evolving plugin: agent hot-mounts/persists ESM Cordis plugins at runtime via evolve_add/evolve_remove/evolve_list, letting it grow or prune tools and behaviors within a session.

Self-evolving team memory

Native local Taskboard plugin for DeepSeek Harness. SQLite-backed projects, Agent claim/review, and a native Web UI — no iframe, no second chat runtime.

Open task handoff protocol for DeepSeek Harness, WorkBuddy, Claude Code and Codex — verified state, not chat logs

Evidence-first deep research workspace — durable project/plan/evidence/report state with model tools and a Web view.

Embedded task-management engine — capture wall, decision ledger, Linear-style issues with evidence-driven lifecycle, history sync and LLM usage ledger.

Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap (bash+read), then full Standard tools after the first tool call or reply

Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model

Native WeShop Cordis plugin for DeepSeek Harness. Allow you to use infinite canvas with infinite creative skills.

Lightweight requirement alignment for DeepSeek Harness — align important decisions before execution without a full spec workflow.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

GitHub Device Flow connect plus an in-conversation PR workflow: a status bar above the composer for create / AI-review / merge, and github_* tools for search, issue and PR read and write.

DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.