Reported News
UNCUT 0.1 is a 7 MB headless coding-agent harness that never trims context or output
UNCUT is an MIT-licensed open-source coding-agent harness first released as v0.1.0 on GitHub on November 1, 2026 (v0.1.1 followed the same day). It is a single static Go binary with four tools that works with OpenAI-compatible endpoints, and its README says "The entire conversation is sent on every model call."
- Changes reported
- 5
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 3
- things we could not verify
- Sources
- 3
- 3 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | The repository was created on November 1, 2026; v0.1.0 was tagged that day and v0.1.1, a Windows reliability patch, about an hour later. Binaries ship for Linux, macOS and Windows on amd64 and arm64. | Reported |
| 02 | It has exactly four tools (read_file, write_file, replace, run_command) and works with any OpenAI-compatible Chat Completions endpoint, including local servers such as Ollama. | Reported |
| 03 | There is no TUI, telemetry, plugin system, automatic retries or context compaction: file contents and command output are never truncated, and a response cut at the provider's output limit makes UNCUT exit with an error. | Reported |
| 04 | It is built for pipelines and CI: piped input is appended to the prompt, --json emits NDJSON events, --session resumes an append-only JSONL history, and --max-steps defaults to 32. | Reported |
| 05 | The project's own Windows measurement reports a 9.461 ms median --version launch and a 7,109,120-byte executable, and its README counts 837 lines of implementation Go. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: UNCUT repository and README on GitHub. We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“The entire conversation is sent on every model call.”
“If the provider cuts a response at its output limit, UNCUT exits with an error instead of presenting a partial answer as success.”
What we have not verified
- We did not install UNCUT or run it against a model.
- The launch-time and size numbers are the project's own, measured on one Windows machine; we did not reproduce them.
- Because the full history is sent on every call, token cost on long sessions grows with every step; we did not measure it.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- UNCUT repository and README on GitHubprimary source · fetched 2026-11-04
- UNCUT benchmarksprimary source · fetched 2026-11-04
- UNCUT v0.1.1 releaseprimary source · fetched 2026-11-04
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/uncut-0-1-lossless-headless-coding-agent-harness.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.