Chain tools into one call.
Declare a pipeline in folder.yaml — the agent triggers the whole chain
with a single echo / cat. No per-step JSON, no per-step model turn.
A virtual filesystem alternative to MCP — built in Rust, zero dependencies for tool authors.
1 round trip per workflow, not N.
Declare a chain of steps in folder.yaml. The agent writes once,
reads once — the kernel runs the pipeline. A 5-step chain becomes
one model turn, not five.
|
folder.yaml — declare the chain
# tools/weather/folder.yaml
files:
- name: report
type: write_invoke
pipe: [fetch_data, translate, format]
# 3 steps, 1 endpoint
|
agent — fire the whole chain
echo "London" > \
.livefolders/tools/weather/report
cat .livefolders/tools/weather/report
# → fetch → translate → format,
# all in one round trip
|
cat runs, the final result is ready. No polling, no glue code,
no stale data.
A 5-step chain is one model turn, not five. The agent writes once and reads once — the kernel runs the pipeline.
Stages hand bytes to each other on stdin/stdout — no re-serializing through the model, no per-call validation overhead.
ls, cat index.md, cat how_to.md. Tool docs load only
when the agent needs them, instead of every schema squatting in the context window.
Agents already know |, xargs, tee. Composing tools
doesn't require a new protocol.
LiveFolders mounts a virtual filesystem on your machine. Every tool you install appears as
a directory of plain files. An LLM reads a file to call the tool — no JSON protocol,
no SDK, no special client. Any agent that can run cat or echo can use it.