tmcra-plugin-deepseek-harness
TMCRA lifecycle project memory integration for DeepSeek Harness across sessions and apps.
Install
$ dsh plugin --profile web add https://github.com/reshuibuduo/tmcra-plugin-deepseek-harness/releases/download/v1.0.0-rc.1/dsh-tmcra-memory-1.0.0-rc.1.tgzPlugin 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
- Recalls user-global and project-specific memory context before model turn execution
- Performs role-separated writeback of user prompts and assistant completions
- Shares project memory across distinct Harness sessions and external TMCRA-connected tools like Codex
- Derives deterministic project scopes from Git origin, Git directory, or workspace path
- Redacts common API keys, secrets, tokens, and sensitive URLs before transmission
- Provides a crash-safe local outbox and fail-open recall handling on network issues
- Supports local embedding/reranker model profiles and separate OpenAI-compatible background providers
Useful For
- Maintaining ongoing project state, decisions, and debugging history across multiple DeepSeek Harness conversations
- Sharing contextual memory and progress between DeepSeek Harness and Codex sessions
- Preserving context across primary agents and subagents during long multi-step workflows
Who It Fits
- Developers working on long-running multi-session coding projects with DeepSeek Harness
- Users collaborating across multiple AI coding tools using TMCRA shared memory
Documented Limitations
- Requires a TMCRA account or local model deployment setup
- Does not automatically backfill historical Harness conversations prior to plugin activation
- Account connection and provider setup rely on external browser and CLI workflows rather than native Harness UI settings
- Pinned to and tested with DeepSeek Harness 0.1.1-rc.2
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 3 runtime, 26 development, 5 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
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
- reshuibuduo/tmcra-plugin-deepseek-harness
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 9f77e6f · 2026-09-05
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-05
- Last release
- 2026-09-03
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.
View plugin →Persistent semantic memory layer for DeepSeek Harness backed by Markdown and Milvus.
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 →