minta
Context quality and memory governance layer for AI agents with DeepSeek Harness integration and MCP support.
Install
$ # DeepSeek Harness: dsh plugin --profile web add @xxinchen/dsh-plugin (or connect via MCP → docs/dsh-integration.md)Plugin 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
- Context lifecycle management detecting stale, conflicting, redundant, or fragmented memories
- DeepSeek Harness integration via MCP client bridge and custom agent presets
- Inbox and counter-example capture for human-in-the-loop rule promotion
- Calibrated confidence gating preventing over-claiming in agent reasoning and research tasks
- Local vector semantic search with type-specific decay models
Useful For
- Maintaining reliable, deduplicated, and up-to-date working memory across agent sessions
- Preventing AI hallucination and contradictory reasoning using staged claim gates
- Managing research literature checklists and compliance evaluations inside DeepSeek Harness workflows
Who It Fits
- AI agent developers requiring structured memory lifecycle governance
- DeepSeek Harness users needing long-term memory with automatic conflict detection
- Researchers managing complex workflows with strict compliance checklist requirements
Documented Limitations
- Requires running the local Minta Python backend service and embedding models
- Write-path memory operations require configured and registered API keys
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.
GitHub reports the repository license as Apache-2.0.
No root package.json was captured in the latest GitHub snapshot.
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
- xinchen03/minta
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 4255d6e · 2026-10-27
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
- 12GitHub stars
- Forks
- 3
- Open issues
- 3
- Last commit
- 2026-10-07
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Agent-native multi-market trading terminal and quantitative research plugin bundle for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →