dondai44423 /donsetch
Web fetch, search, and crawl for AI agents. Built from scratch in Rust. No keys, no accounts. AGPL v3.
★ 1,000⑂ 66👁 4⑃ 312● 124▤ 107
+2
Daily
1,000
stars
66
forks
4
watchers
312
prs
124
issues
107
releases
README
DonSeTch
The web tools your agent needs.
Search, fetch, crawl, and screenshot. One local Rust binary. No required API keys or accounts.
Install ·
Tools ·
Design ·
Proxies ·
Limits ·
Docs ·
Sponsor
Find a source, read the useful part, follow a link, check a claim. DonSeTch gives agents that web loop over MCP or from your terminal, with about 2,000 tokens of tool schemas.
Page reads launch no browser. Real client profiles, learned routes, and embedded V8 handle the fetch. Chromium is used separately for screenshots. Search needs no model download.
Start here
1. Install
bash
npm install -g donsetch
donsetch doctor
The installer downloads a SHA256-verified release binary. No Rust toolchain needed. Linux, macOS, and Windows are supported.
Homebrew, Pi, DeepSeek Harness, or build from source
| Install | Command |
|---|---|
| Homebrew · macOS/Linux | brew tap dondai44423/donsetch && brew install donsetch |
| Pi native extension | pi install npm:donsetch |
| DeepSeek Harness plugin | dsh plugin --profile web add github:dondai44423/donsetch-dsh |
Pi and dsh register native tools. For source builds, platform requirements, Docker, or installer troubleshooting, see the setup guide.
2. Connect your agent
Add this to your MCP client's server configuration, then restart the client:
json
{
"mcpServers": {
"donsetch": {
"command": "donsetch",
"args": ["mcp", "--supervised"]
}
}
}
Works with Claude Code, Cursor, OpenCode, and other MCP clients. Configuration formats vary; donsetch doctor --mcp prints registration examples using the binary's absolute path. --supervised restarts the stdio daemon after a crash.
Need an HTTP endpoint? Run donsetch mcp --http --port 8765 and connect to http://localhost:8765/mcp. HTTP setup and authentication →
3. Try it
bash
Find sources.
donsetch search "rust async cancellation" --intent code
Read the passages that answer.
donsetch fetch https://docs.python.org/3/library/asyncio-task.html \
--focus "cancel a task"
Map a documentation site.
donsetch crawl https://docs.python.org/3/ --mode map --topic asyncio
The CLI and MCP tools use the same engine. No account setup sits between install and first use.
Worth keeping in your toolkit? Star the repo. It helps other agent builders find it.
Four tools. One process.
| Tool | Use it for | Useful controls |
|---|---|---|
| web_fetch | Pages, PDFs, structured site records, or up to 12 URLs at once | must_contain, focus, toc, section, since_last |
| web_search | Ranked sources and evidence snippets, keyless by default | intent, lang, max_results, read |
| web_crawl | A site map or a bounded crawl with resumable progress | mode, focus, max_pages, resume |
| web_screenshot | A rendered PNG through an installed Chromium-family browser | full_page, wait_ms, deadline_ms |
Your agent chooses what to read next. DonSeTch supplies the tools.
Read less. Keep the evidence.
Every view works over Top issues
Discussions
#402hound vs donsetch1 comments · 2026-11-03#170Exploring a Lightweight Multi-Stage Ranking Pipeline for DonSeTch0 comments · 2026-09-10#47This is genuinely useful even for major big corpo AI chats1 comments · 2026-08-25
Latest release
v5.4.1 v5.4.1 2026-11-15DonSeTch v5.4.1 Fixed - The updater downloads release assets over parallel ranges. A single stream from the release CDN is throttled per connection on some networks — measured 4-28 KB/s while the same 40 MB asset came down at 200+ KB/s over several connections — so an upgrade that should take minutes gave up after twenty. The downloader now probes with one range request, splits what is missing across eight connections, resumes each segment on a stall, and keeps the buffer a resumable prefix for the next route; a server that ignores Range is streamed exactly as before. An asset bel