caveman-ai/trim-1

trim-1 is a small model that decides which lines of a context an AI agent needs for its current ask, and drops the rest.

Give it a context (a tool result, a file, a log, a long chat) and the current query. It returns the context's own lines, in their original order, with a short marker wherever lines were removed. It never rewrites or summarizes a line, so identifiers, paths and error text come through exactly as they were.

• 1.2 MB. 712 gradient-boosted trees, not a neural network.
• Milliseconds on one CPU core. No GPU, no network call.
• Deterministic. No sampling and no randomness: the same context and query give the same output.
• No dependencies. Pure Go, standard library only. The model is embedded.

The model card, with benchmark results and limits, is on Hugging Face: caveman-so/trim-1.

Needs Go 1.23 or newer.

go install github.com/caveman-ai/trim-1/cmd/trim@latest

From the command line:

trim --query "why does the build fail" build.log > build.trimmed.log

cat long-document.md | trim --query "what is the refund policy" --point balanced

The trimmed context goes to stdout. A one-line summary goes to stderr:

trim: kept 246 lines, removed 189, 47831 -> 36344 bytes

From Go:

import trim "github.com/caveman-ai/trim-1"

res := trim.Compress(context, query, trim.Options{Point: "balanced"})
fmt.Print(res.Output)

trim.Score(context, query) returns every line with its keep probability, if you want to make the selection yourself.

--point decides how hard trim-1 cuts: conservative, balanced (the default) or aggressive. Cutting harder costs quality, because every removed line is one the model can no longer read.

• Long-document retrieval is what trim-1 is for. Use balanced.
• Coding-agent tool outputs are short and dense. Stay at balanced or conservative and expect small savings.

The model card has the numbers behind this.

trim-1 fails closed. It returns the context unchanged, and says why on stderr, when:

• the query is blank,
• the context is under 2,000 bytes,
• the context is over 8 MiB or 200,000 lines,
• the context already has a removal marker line, such as trim-1's own output,
• the cut would remove less than 10% of the bytes.

The trim command exits with status 2 on a missing --query or an unknown --point. Flags go before the file name.

go test ./...

TestPredictionParity checks the Go tree evaluation against the training library's own predictions, bit for bit. TestGolden pins the full output on a sample log.

Apache-2.0. model.go includes a copy of Go's math.Exp, under the BSD license in LICENSE-go. trim-1 is the model inside Caveman.