managed-agents
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
144 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
Structured memory engine for DeepSeek Harness. Offline semantic search, entity-attribute-timeline, autoDream self-consolidation, and human-editable Markdown storage.
DeepSeek Harness Blender production, reconstruction, validation, and export plugin
Cordis /hongtou command: two-phase pipeline (LLM structured JSON + deterministic Word 2003 XML template rendering)
Deep reading & summarization for DSH: books/papers/videos/web → structured Obsidian notes. Plugin parsers, MapReduce deep-read, JSON Schema output, idempotent cache.
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
Unofficial Plannotator integration for DeepSeek Harness: annotate plans inline and return structured feedback to the waiting coding agent
TaskPack: an open, offline task-handoff container. Task Passport is the durable state; TaskPack is the box it travels in.
Four-source migration wizard: copy Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DeepSeek Harness as resumable sessions — copy-only, approval-gated, idempotent
Generate and display images inline in the DSH chat via API channels or local CLIs (mmx / codex / agy), and read images into structured JSON evidence (OCR / layout / semantics) on any model — with backend probing and a bundled recovery skill.
Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. DSH plugin host; Python stdlib + Markdown core. Zero database / vector service / external service dependencies.
DeepSeek Harness plugin bundle: optimize raw instructions into professional Role / Task / Context / Format prompts through the harness llm service
Feynman learning-mode plugin for DeepSeek Harness: /learn on|off, structured lesson cards, rich HTML teaching.
Edit ~/.dsh/AGENTS.md (global rules) from the web settings panel.
Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets
Tensorlake sandbox execution providers for DeepSeek Harness
CodeGraph for DSH — registers native `codegraph_*` tools (core surface: status/init/sync/explore; full surface adds query/node/files/callers/callees/impact/affected/index/uninit) wrapping the `codegraph` CLI, plus a prompt front-load hook that steers structural CodeGraph context into structural prompts, so the DSH agent can bootstrap, maintain, and query a pre-indexed code knowledge graph without grepping files.
Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness
DSH web plugin: per-host personalization — global custom instructions, local long-term memory (collect / retain / integrate / manage), and reply tone presets.
DeepSeek Harness web notifications for approvals, structured questions, and task outcomes.
DSH diff tool: structured comparison of text/JSON/CSV/Markdown plus unified diff generation and in-memory patch validation. Zero-dependency, read-only.
One-way structured conversation, project, MCP, memory, and context migration between Codex and DeepSeek Harness. Codex 与 DSH 的单向结构化迁移插件。