v1.0.0 ⁄ released 2026-06-03 ⁄ MIT ⁄ a substrate for SkDD

Infinite context.
For every agent
you ever hire.

Capture decisions while you work. One CLI command per choice — no after-the-fact writeup. Every new agent (Claude Code, Cursor, Codex, Cline) gets the full why-behind-the-code in one read. Markdown links between docs are checked on every PR; the project tree regenerates on every log. Documentation that can't go stale.

principles.

i.

captured while you work

One logmind log per choice — written, committed, and routed to the right branch file in one command. Reasoning lives next to the code, in git.

ii.

auto-documentation

AGENTS.md is canonical; per-tool files become two-line stubs pointing at it. Every relative [link](path.md) is verified on every PR. The project tree regenerates on every log.

iii.

always in sync

Decisions, timeline, project tree — they update together. Rebase against main? Fresh clone? Multi-commit amend? They stay synced. CI never catches you with a stale derived doc.

iv.

infinite context for agents

Any agent that supports AGENTS.md inherits the decision history, the tree, the why-behind-the-code. Onboarding a new agent takes one read.

the loop.

Logmind is one part of an end-to-end agentic dev loop. The tools compose; each can stand alone.

Skills-driven development (SkDD) gives you a methodology and skill primitives. logmind captures the why behind every change as you work, builds and tests the skills you forge, and keeps your derived docs in sync across rebase / merge / fresh clone. clud-bug runs your skills against every PR — every finding cites the skill that motivated it. The loop closes when logmind logs the review outcome and surfaces refinement patterns for the next iteration.

End-to-end agentic auto dev: write skills first → log the why → run them against PRs → iterate based on usage. The tools work independently; better together.

measured.

Logmind costs fewer tokens than the git workflow it replaces. Anyone can run the benchmarks. Every release.

Decision logging only matters if it stays cheaper than the alternative. We measure four ways every release: per call, worst case, per session, org cumulative. CI gates on net-saver across all four.

$ python -m bench
  per-call       -18% bytes vs git equivalent      ✅ saver
  worst-case     -58% even on never-read           ✅ saver
  per-session     informational (4-angle frame)    ℹ info
  org-cumulative  informational (rollup)            ℹ info
ok: 4-angle Q7-logmind compliance

The two informational angles share a thin baseline (read-event accounting needs aggregation); the two gating angles are the load-bearing checks. python -m bench ships in the repo — no setup, no API keys.

install.

v1.0 ships as a single signed + notarized Go binary. Brew or curl, pick whichever lives closest to your other dev tools.

01
homebrew
$ brew install thrillmade/tap/logmind
02
curl
$ curl -fsSL https://logmind.dev/install.sh | sh
03
agent skill
$ npx skills add -g thrillmade/logmind-skill
04
verify
$ logmind --version

logmind --version should print logmind 1.0.0 (spec 0.1.0). The agent skill (03) is optional but recommended — it teaches Claude Code, Cursor, Codex et al. when and how to call logmind log in any project that has logmind installed.

deprecatedPython wheel · frozen at v0.6.16
$ pip install 'logmind==0.6.16'

pip install logmind is frozen at v0.6.16 — the last published Python release. New installs should use the Go binary above. The PyPI package is kept on PyPI only to honour old pinning; it receives no further updates, no security backports, and no feature parity with v1.0+. Migrating? See the migration guide for the one-line CI swap.

quickstart.

Init once per repo. Then log every meaningful choice. Branch routing happens automatically.

~ ⁄ feat__auth
$ logmind init
$ git checkout -b feat/auth
$ logmind log "JWT for stateless API auth" \
    -r "horizontal scaling without session store" \
    -a "server sessions in Redis" \
    -i "rotate signing keys quarterly"
✓ wrote docs/decisions-branches/feat__auth.md

“Every agent you’ve ever onboarded asked the same questions because the answers lived in someone’s head. logmind moves them into git, into AGENTS.md, into the tests that run on every PR— so the next agent never has to ask.”

— design intent