dsh-llm-agent-bridge
Bridges Anthropic's Claude Agent SDK into DeepSeek Harness as a selectable LLM provider across all modes.
Install
No clear install command was found in the current repository evidence.
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
- Registers Claude as a selectable LLM provider across all DeepSeek Harness modes
- Preserves DSH native prompt, approval mechanisms, and execution sandbox by handing tool execution back to DSH
- Projects Claude adaptive thinking and reasoning streams into native DSH stream chunks
- Displays Anthropic plan usage limits directly within the composer tool row
- Maintains cross-turn context when switching providers mid-session via dsh-context blocks
- Includes per-turn session telemetry guards to prevent forwarding Claude outputs to default OTLP exporters
Useful For
- Using Claude models (Opus, Sonnet, Haiku) as the primary reasoning engine within DeepSeek Harness
- Switching between DeepSeek and Claude models mid-session while retaining conversation history and tool trajectories
- Executing local development tasks with Claude reasoning inside DSH's sandboxed tool execution runtime
Who It Fits
- DeepSeek Harness users with existing Claude subscriptions or API access
- Developers seeking Claude reasoning capabilities within DSH's structured tool and approval ecosystem
Documented Limitations
- Requires authenticating with Claude Code CLI or providing an ANTHROPIC_API_KEY
- DSH-side conversation compaction or edits made after Claude has seen them are not replayed into the Claude session
- Reading usage counters consumes a Claude Code control session, which may be hidden if experimental SDK calls fail
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 2 runtime, 14 development, 3 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
- daveycodez/dsh-llm-agent-bridge
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- c8811e9 · 2026-09-18
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
- 1
- Open issues
- 0
- Last commit
- 2026-09-12
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →