@elves-ai/dsh-web-search-firecrawl
Firecrawl-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
86 results
Firecrawl-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
Unified web search for the DeepSeek Harness seam (ctx.web): DeepSeek (official), Tavily, Brave, Serper, SerpApi, Exa, SearXNG, Scavio, and Firecrawl backends
Tavily-backed WebSearchProvider for the DeepSeek Harness web seam (ctx.web) - keyless mode supported, no API key required
元压缩:模型自己决定何时、如何压缩自己的上下文——列 surface、选区间、以自写文本替换;替换走官方 compaction 事务(检查点、配对平衡、可重建)。Meta-compaction: the model directs its own context compaction through the official compaction seam.
DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams
AWS Kiro (CodeWhisperer) adapter for the DeepSeek Harness LLM seam: Claude and open-weight models through one signed-in Kiro account
OpenCode-style web search (Exa / Parallel MCP) provider for the DeepSeek Harness ctx.web seam. Gives any model, including opencode-go's deepseek-v4-flash, a working web_search tool without a DeepSeek official API key.
Firecrawl-backed search provider for the DeepSeek Harness web capability seam (ctx.web)
Named user credentials for DeepSeek Harness: model-facing credential tools, secrets behind the ctx.credentials seam, DSH_CM_* shell variables, and a Settings → Credentials page
DeepSeek Harness plugin: auto-detect secrets pasted into the composer, store them in the official credentials seam, and send [secret:REF] placeholders to the model instead of the value.
Thin on-demand context-retrieval layer for DeepSeek Harness: context_query / context_slice / context_grep tools over the sessionQuery and subprocess seams.
LongCat (LongCat-2.0) adapter for the DeepSeek Harness LLM seam — 1M context, thinking mode, tool calling
A macOS Keychain-backed CredentialProvider for agent harnesses, initially compatible with DeepSeek Harness.
Sync cc-switch provider profiles (Claude Code / Codex relays) into DeepSeek Harness as llm-pi-ai routes, credentials stored via the DSH credential seam.
OpenTelemetry traces backend for the DeepSeek Harness telemetry seam: folds agent session events into OTLP span trees
Brave Search API provider for DeepSeek Harness web capability seam (ctx.web)
Multi-provider AI balance widget for the dsh web sidebar: a live, auto-refreshing balance pill plus a detail popover listing DeepSeek and any added providers (MiMo etc.). Keys are stored per-machine in ~/.dsh/ai-balances.json and resolved from the local credential seam, never hardcoded.
ACP LLM adapter + ACP Servers settings UI: drives external Agent Client Protocol servers as model providers on the DeepSeek Harness LLM seam, with a web settings page for browsing the ACP registry and managing configured servers
Seatbelt (libsandbox) sandbox provider for the DeepSeek Harness sandbox seam on macOS: a cordis plugin that replaces @deepseek-ai/dsh-sandbox-local's seatbelt rung via a prebuilt seatbelt-run launcher — no dsh source changes, no PR required
Ollama-backed search provider for the DeepSeek Harness web capability seam (ctx.web): adapts Ollama /api/web_search into dsh web_search tool.
terminal_search tool for dsh: locate lines in large persistent-terminal scrollback by regular expression, composed over the public terminal read seam.
Kimi K3 connector plugin for the DeepSeek Harness llm capability seam.
pi-web-access for the DeepSeek Harness: multi-provider web search with automatic fallback (SearXNG → Tavily → Brave → keyless DuckDuckGo) plus URL content extraction, wired into the web seam so the built-in web_search tool is powered by piwa. Search engine toggle and API keys are configurable from the DSH settings page.
Kimi (Moonshot AI) chat-completions adapter for the DeepSeek Harness LLM seam — three routes: kimi-code (Kimi Code subscription), kimi-cn, kimi-global