Install
$ dsh plugin --profile web add dsh-knitPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Deterministically ranks workspace docs, code, and media using local BM25 and IDF without external model calls
- Structures context into primary, supporting, and related tiers with explicit, verifiable citation reasons
- Integrates into DeepSeek Harness right sidebar with code syntax highlighting and HTTP Range media streaming
- Provides the knit_docs tool for AI agents to query structured task context with line-level matches
- Tracks document lifecycle states (unread, read, updated after read, re-read after modification)
- Offers manual pinning and exclusion of workspace items with optional storage persistence
- Includes optional hybrid retrieval mode supporting local or OpenAI-compatible embedding endpoints
Useful For
- Surfacing relevant architecture docs, code files, and assets automatically based on active conversation topics
- Allowing AI coding agents to locate context targets via knit_docs without relying on brute-force glob and read cycles
- Monitoring whether an AI agent actually read recommended context and whether files changed after reading
Who It Fits
- Developers working on multi-file codebases inside DeepSeek Harness
- Teams using autonomous AI coding agents needing structured workspace context without high token overhead
Documented Limitations
- Retrieval degenerates to modification time ordering if conversations are too short (1-2 messages)
- Code context indexing is capped at 300 candidates and inspects only the first 8 KB of file content
- Chinese tokenization relies on character n-gram approximations rather than external segmentation libraries
- Hybrid semantic search is disabled by default and requires user-provided embedding endpoints
- Right sidebar UI open state is stored in memory and resets across fresh sessions
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- PolinniZhong/dsh-knit
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- b8cd907 · 2026-10-17
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 54GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-16
- Last release
- 2026-10-13
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →DeepSeek Harness integration for ego-lite Chromium browser, providing 33 structured automation tools and a real-time visual watch panel.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →Cost and token tracking plugin for DeepSeek Harness featuring session budgets, provider balances, and coding plan quotas.
View plugin →