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.
93 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
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.
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.
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.
Feynman learning-mode plugin for DeepSeek Harness: /learn on|off, structured lesson cards, rich HTML teaching.
Tensorlake sandbox execution providers for DeepSeek Harness
DSH diff tool: structured comparison of text/JSON/CSV/Markdown plus unified diff generation and in-memory patch validation. Zero-dependency, read-only.
Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness
DeepSeek Harness web notifications for approvals, structured questions, and task outcomes.
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。
Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.
Allow, ask, or deny DeepSeek Harness tool calls before execution
Agent trajectory governance & anomaly diagnosis for DeepSeek Harness: rebuild structured multi-branch trajectory trees from the session/event feed, keep observation-layer snapshots, and run three temporal anomaly strategies (loop deadlock / invalid retry / goal drift).
Structured long-term memory system for DeepSeek Harness -- unit-based brief/full pairs with auto-injection
Observe-only hash-chained evidence receipts for DeepSeek Harness
DSH plugin: connect to a NebulaGraph 5.0 server and execute GQL queries, returning results as structured rows plus an ngql-style table render. Bundles the gql-query-generator skill.
Structured, safe Git tool family for DeepSeek Harness: status/diff/log/branch/stage/commit/stash/show/fetch/pull/remote/checkout with a destructive-command guard.
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.