jackulau/coding.sh

Your sessions stay on your machine.
Docs ·
Quickstart ·
Supported agents ·
Changelog ·
Discussions ·
Report a bug
sh
curl -fsSL https://coding.sh/install | sh
One Claude Code session in the local viewer, with the diff it made and the tests it ran. Sample data, generated by sample-sessions.mjs .
coding.sh records what your agents do: prompts, tool calls, file changes, model calls, latency and
tokens. It goes into a SQLite index on your machine. You browse it in a local viewer, query it from
the CLI or from your agents over MCP, turn failures into evals, and compare changes with paired
statistics. It covers the same ground as LangSmith or Braintrust, but capture, storage and the
viewer stay on your machine unless you add a remote sink.
MIT licensed, no runtime dependencies, Node 22.15 or newer.
## Quickstart
The install command above downloads the latest GitHub release, runs coding.sh init, then opens
the viewer. init finds your agents, shows one plan and asks once. It points their hooks at
coding.sh, registers the MCP server where the agent supports it, and backs up every config file it
edits. coding.sh init --dry-run prints the plan without writing anything (--diff adds the edits), and
coding.sh uninstall removes the hooks and MCP entries again.
Then use your agents as usual. Sessions show up on their own, with no ingest step. To pull in
sessions from before you installed:
sh
coding.sh ingest --backfill
coding.sh is not on npm yet, so npm install -g coding.sh doesn't work today. Installing from
source, updates and uninstall: docs/guides/install.md.
## What you get
Record. Hooks and transcripts capture each session, including subagents.
coding.sh run -- wraps any other agent and snapshots the repo before and after.
coding.sh collector takes OpenTelemetry from agent frameworks and apps.
Measure. Every session has its turns, tool calls, model calls, tokens, latency and outcome.
Sessions that edited code and never ran a check get a no-verification flag.
sh
coding.sh sessions # recent sessions
coding.sh show latest # timeline with turns, tools, subagents and latency
coding.sh search "rate limit" # full-text search over prompts, replies and tool calls
coding.sh usage --by model # tokens, turns and cache hits
coding.sh ui # the local viewer
Every command takes --json. coding.sh mcp gives your agents the same data as MCP tools.
More in docs/guides/explore.md.
Compare. Turn a failed session into a replayable eval with coding.sh eval new, and check
that its verifier is fair with coding.sh eval validate. Run experiments over versioned datasets
with code graders or calibrated LLM judges. coding.sh exp compare and coding.sh compare A/B
prompts, harness files and models with paired statistics. Tool evals and multi-agent workflow
runs are covered too. More in docs/guides/evals.md.
Benchmark. coding.sh bench draws new cases every day from a script, your failed sessions,
GitHub issues or a sitemap. Every contender gets the same frozen set in random order, and
bench report writes a static page with the trend, today's head to head and where each one
fails. More in docs/guides/benchmarks.md.
Production. coding.sh serve runs ingest, the viewer and the API on one port, backed by