dsh-run-guard
Agent run-rhythm guard for DeepSeek Harness: reasoning dead-loop interception (guard) + automatic continuation after premature stops (continue)
132 results
Agent run-rhythm guard for DeepSeek Harness: reasoning dead-loop interception (guard) + automatic continuation after premature stops (continue)
Interactive multi-agent council and prompt arena for DeepSeek Harness
Password-gated public access for the Web GUI via Cloudflare Tunnel: a loopback password gate (login page + HMAC cookie) in front of the webserver, published by spawning cloudflared in quick or named-tunnel mode - tells the shell and the model the public URL
Web-switchable agent loop engine selection for the DeepSeek Harness - out-of-tree plugin (Claude Code / Codex / Pi / Kimi Code drivers) maintained by @kuun993, zero main-repo changes
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
DeepSeek Harness host plugin that wraps the Playwright CLI: install browsers, run tests, and open the HTML report from the agent loop.
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)
Recursive Self-Improvement (RSI) engine for DeepSeek Harness: a bounded perceive → integrate → verify → repair → propose loop that keeps a downstream desktop app in sync with the fast-moving upstream harness. AI for AI — DSH maintains DSH.
Local-first task outcome ledger & acceptance plugin for DeepSeek Harness (DSH): evidence-backed verification of task completion, zero extra model cost, user-owned sidecar data. 任务结果账本与验收插件:机械证据验收、默认零额外 token、数据本地持有。
CI doctor plugin for DeepSeek Harness: watch GitHub Actions failures, diagnose logs into structured findings, and drive the fix loop
DSH recap plugin: distills every model request (turn:step) of a session into one sentence, appended incrementally with a cache-friendly prompt (history sentences first, new delta last). Side-effect-free for the agent loop.
A reusable DeepSeek Harness bundle for evidence-driven memory, orchestration, benchmark operations, repository audits, and plugin release workflows.
DeepSeek API balance pill for the DSH Web GUI: shows remaining credit in the left sidebar footer with low-balance alerts, spend history, and a one-click top-up link. The API key never leaves the host process — the host half resolves it through the dsh credentials service and queries api.deepseek.com/user/balance; the browser half only fetches redacted balance JSON from a loopback route.
SliceAgent concrete agent loop plugin for the DeepSeek Harness — a drop-in AgentFactory/Agent implementation whose context engine is the bounded slice
DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel
DeepSeek Harness frontend runtime verification: detect, run, preview, interact, diff, and prove local web apps.
AI turns repeated dev commands, prompts, and instructions into one-click DeepSeek Harness actions.
Offline DeepSeek request, tool-loop, reasoning_content, and SSE diagnostics for DSH
Persistent wallpaper skin for the dsh web profile: static image or muted looping video as the app background, with translucent panels. The path is editable live from Settings → Plugins.
DeepSeek Harness plugin: provider account balance inside each Models settings row, queried through a loopback-pinned RPC channel with the stored API key kept on the host
Popper: a falsification-driven correction loop for agent sessions — claim commitment, gate falsification, and mutually exclusive hypothesis revision, with an append-only evidence ledger
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
Agent loop rate limiter — prevents TPM/RPM limit violations by intercepting the LLM streaming pipeline and adding adaptive delays between requests