Apache-2.0, zero-dependency, git-backed failure-memory library (290 lessons) that plugs into DeepSeek Harness via a dedicated MCP adapter exposing deepseek.recovery.* tools.
DSH integration
Compatible
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
Give DeepSeek Harness a shared failure-memory so it searches verified debugging lessons instead of re-debugging known errors
BM25 keyword matches across 290 indexed lessons (problem → root cause → fix → verify), served through the DeepSeekHarness MCP adapter as `deepseek.recovery.*` tools
DeepSeekHarness users who want harness-level failure recovery without a server, database or extra dependencies
Search 290 verified failure-recovery lessons locally from the command line
Zero-dependency BM25 keyword search results over Markdown lessons, runnable with Python stdlib only after `git clone`
Developers and agents debugging real failures (DCO, pip, token, MCP, encoding, CI) who want an offline-first lesson lookup
Feed unmatched failures back into the network without a GitHub account or email
Redacted intake submitted via the `misakanet_submit_intake` remote MCP tool, becoming a maintainer-visible GitHub issue labeled `intake`, `mcp-intake`, `pending-review`
Agents whose task stalls on a failure with no matching lesson; no GitHub account, email, Bearer token or browser required
02How to install into DeepSeek Harness
Prerequisites
- Python 3.10+ (badge: python-3.10+) — the core engine is zero-dep, pure Python stdlib
- git — lessons ship as Markdown files in the repository
Installation steps
- 01
Clone the repo: `git clone https://github.com/Ikalus1988/MisakaNet.git && cd MisakaNet`
$ git clone https://github.com/Ikalus1988/MisakaNet.git && cd MisakaNet
- 02
For DeepSeekHarness, run the recovery adapter: `python3 scripts/mcp_deepseek_adapter.py`
- 03
Alternative: run the standard MCP server `python3 scripts/mcp_server.py` and add it to your MCP config
- 04
Optional local search: `python3 search_knowledge.py "your error here"`
Verify the integration
- Run the smoke check: `python3 scripts/misakanet_cli.py smoke` — the README's 'Contribute in 3 minutes' flow uses it to verify it works
03DSH integration and capability boundaries
MCP-compatible adapter (`python3 scripts/mcp_deepseek_adapter.py`) exposing `deepseek.recovery.*` tools for harness-level failure recovery
DeepSeekHarness recovery adapter
harness-level failure events from DeepSeekHarness→`deepseek.recovery.*` MCP tools for failure recovery inside the harness
runs a local MCP adapter process (`python3 scripts/mcp_deepseek_adapter.py`)Zero-dependency BM25 lesson search
an error message or query string→matching failure-recovery lessons (problem → root cause → fix → verify) via pure-Python BM25 retrieval
MCP server for any MCP client
MCP config of Claude / Codex / local agents→lesson search and intake tools, e.g. ask: "Search MisakaNet for pip install timeout"
runs a local MCP server process (`python3 scripts/mcp_server.py`)Remote MCP intake (no account)
a redacted failure description→`misakanet_submit_intake` call to `https://misakanet.org/mcp` creating a maintainer-visible GitHub issue for review
network call to the remote endpoint https://misakanet.org/mcpcreates a GitHub issue labeled intake / mcp-intake / pending-review; submissions must be redacted (no secrets, no raw logs)
04Who is it for? When not to use it?
Good for
- DeepSeekHarness users who want harness-level failure recovery without a server, database or extra dependencies
- Developers and agents debugging real failures (DCO, pip, token, MCP, encoding, CI) who want an offline-first lesson lookup
- Agents whose task stalls on a failure with no matching lesson; no GitHub account, email, Bearer token or browser required
Not for
- Lessons are community-contributed, so retrieved commands must be reviewed before execution — the README tells users to always sandbox their agent before running retrieved commands.
05Compatibility, maintenance and safety notes
- Lessons are community-contributed, so retrieved commands must be reviewed before execution — the README tells users to always sandbox their agent before running retrieved commands.
- MisakaNet is purpose-built for failure-recovery knowledge: it is not a general-purpose memory system, not an agent runtime, and not a vector database or RAG system — BM25 keyword search only.
- Local clone + search is fully offline, but the remote MCP endpoint (https://misakanet.org/mcp) and lesson intake require network access; intake submissions are reviewed by maintainers before publication.
Apache-2.0 · actively maintained (latest release v2.17.1, 2026-08-16; last push 2026-08-19)
06Frequently asked questions
How does MisakaNet connect to DeepSeek Harness?
Via the dedicated DeepSeekHarness MCP adapter: run `python3 scripts/mcp_deepseek_adapter.py` after cloning. It is an MCP-compatible adapter exposing `deepseek.recovery.*` tools for harness-level failure recovery. Full setup, verification and degradation strategy are documented in docs/integration/deepseek-harness.md.
Is it native to dsh or an MCP tool?
It integrates as an MCP tool set, not a native runtime. The standard MCP server (`python3 scripts/mcp_server.py`) also works with Claude, Codex and other local agents; a hosted endpoint is available at https://misakanet.org/mcp.
What do I need installed first?
Python 3.10+ and git. The core engine is zero-dependency — pure Python stdlib, no vector database, no server, no database. Optional extras exist via `pip install misakanet[semantic|hub|feishu]`.
Does it send my data anywhere?
Local clone and search are offline: `git clone` + `python3 search_knowledge.py` with no prompt leaking and no raw logs stored. Only the optional remote MCP intake calls https://misakanet.org/mcp, and submissions must be redacted — maintainers review them before any publication.
What are the limits?
MisakaNet is a failure-recovery knowledge layer only — not a general memory system, agent runtime or RAG stack — and lessons are community-contributed, so review any retrieved command before running it and sandbox your agent.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
**DeepSeekHarness Adapter** | MCP-compatible adapter exposing `deepseek.recovery.*` tools for harness-level failure reco…
| DeepSeekHarness | `python3 scripts/mcp_deepseek_adapter.py` |
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.