세션 반복 설명 끝, 로컬 토큰 절약 도구 리콜

🔁 Recall — fully-local project memory for Claude Code Claude Code starts every session cold. Recall keeps a local log of your sessions and condenses it into a resume-ready summary — entirely on your machine . No API key, no external model, nothing sent anywhere. It's built for people running Claude Code locally on a subscription: the only AI in the loop is Claude Code itself; the summarization is done by a classical Python summarizer. Why Recall Free on your subscription. It solves the cold-start problem — no more re-explaining the project each session — without a metered summarizer running up a bill. The summary is a local algorithm, not an LLM call, so persistent memory costs you nothing beyond the subscription you already pay for. Saves your usage credits. Two ways: (1) the summary is built locally, so capturing and updating your memory spends zero model tokens; and (2) resuming from a compact context.md (~1–2K tokens) instead of re-explaining the project from scratch each session means far fewer tokens spent per session — stretching your subscription's usage limits (or, on the API, lowering billed credits). Nothing leaves your machine. Your transcripts (code, paths, sometimes secrets) are never sent to any API. Most "memory" tools pipe your context to a model endpoint; Recall makes a privacy guarantee they can't. Zero-friction. No pip install , no local model to run, no key to configure, works offline. It starts working the moment the plugin loads. Two files, written into your project under .recall/ : history.md — the log. Append-only. Every session is captured here as it happens (your prompts, Claude's replies, the files touched and commands run). context.md — the summary. Overwritten by the local summarizer — the condensed "where are we right now" you load into the next session: goal, summary, next steps / open threads , files touched, and where you left off. "Doesn't Claude Code already have memory?" It does — and Recall is complementary, not a replacement. The built-in options solve different problems: CLAUDE.md (and the # shortcut) is hand-written memory: rules and notes you curate, loaded as instructions Claude follows . Great for "how I want you to work," but it's manual upkeep and it doesn't record what actually happened in a session. --continue / --resume replays a prior conversation — full fidelity, but it reloads the whole transcript (token-heavy) and is tied to your local session history on one machine, not a portable, readable digest. Context compaction condenses a conversation within a session; it isn't a durable record you reopen days later. Recall fills the gap between these: an automatic, deterministic record of what each session did , condensed into a compact resume point. CLAUDE.md / # --continue / --resume Recall What it is Hand-written notes & rules Reloads a prior conversation Auto-captured session log + local summary Upkeep Manual None (you pick the session) None — written as you work Holds Instructions to follow The full prior transcript Goal, files, commands, where you left off, next steps Cost to resume Small Large (replays full transcript) ~1–2K tokens (compact digest) Form Markdown you edit Local session state Plaintext in .recall/ — diffable & shareable How Claude treats it As instructions As the conversation Fenced as untrusted reference data In short: CLAUDE.md is how I want you to work ; Recall is here's what we did last time and where we stopped — produced offline, with no model tokens spent. How it works Moment What happens During the session The Stop / SessionEnd hooks append new activity to .recall/history.md . Capture is incremental (only new turns) and fully local. At session start The SessionStart hook surfaces context.md and has Claude ask you two things: resume from the saved context? and keep logging this session? Before you wrap up You run /recall:save . The local summarizer reads history.md and (over)writes context.md . …or automatically Set auto_save_context: "on_end" and context.md regenerates every time a session ends — no /recall:save needed. There is no LLM call anywhere — the summary is produced by TF-IDF + TextRank (extractive summarization) running locally. The summarizer scripts/summarizer.py ranks the most central sentences of your session: TF-IDF sentence vectors a cosine-similarity graph between sentences TextRank — PageRank power iteration over that graph — to score sentences the top N are kept in original order context.md wraps that summary with deterministic facts pulled straight from the transcript and git: the goal (your first ask), files touched, commands run, where you left off, and git diff --stat . No installs required. The whole TF-IDF + TextRank implementation is vendored in summarizer.py . If numpy happens to be importable it's used to vectorize the math (faster on big sessions); if not, an identical pure-Python TextRank runs instead. Same algorithm, same result — numpy is an optional accelerator, never a requirement. The save output tells you which path ran. Commands /recall:save — run the local summarizer → (over)write context.md . /recall:show — print context.md . /recall:log — tail history.md . Configuration — recall.config.json Drop this in your project root to override defaults: Key Default Purpose output_dir ".recall" Where history.md / context.md live. capture_history true Append session activity to history.md . auto_save_context "off" Regenerate context.md when a session ends: "off" or "on_end" . summary_sentences 8 How many sentences the summary keeps. redact true Strip obvious secrets before writing the md files. include_git true Add git diff --stat + recent commits to context.md . max_input_chars 200000 Cap on text fed to the summarizer (oldest dropped). Pause logging for a project without editing config: create .recall/.capture-paused . Delete it to resume. Privacy & security Recall makes no network calls, uses no API key, and loads no third-party model. The summarizer is local Python; the hooks are stdlib-only (numpy is an optional accelerator). It reads your session transcript and writes only under output_dir . Concretely: No credentials, ever. The plugin has zero references to API keys, auth, ANTHROPIC_* , or HTTP. If claude itself shows "Invalid API key" , that's the CLI's own auth — usually a stale ANTHROPIC_API_KEY env var shadowing your subscription login. unset ANTHROPIC_API_KEY (or run env -u ANTHROPIC_API_KEY claude … ). It has nothing to do with Recall. Redaction. A best-effort pass strips common secret shapes (API keys, tokens, .env assignments, PEM keys) before writing, since context.md / history.md may be committed. Best-effort, not a guarantee — review before committing. Hardened git. git diff / log are run with core.fsmonitor , diff.external , hooks, and the pager disabled, so an untrusted cloned repo can't use its own git config to execute code when Recall reads ground-truth. Set include_git: false to skip git entirely. Confined writes. output_dir is forced to stay inside the project; a project-shipped config can't redirect writes to an absolute path or ../.. . Scoped transcript. Recall only reads the transcript for the current project (matched by cwd); it never falls back to another project's sessions. Trust boundary for shared memory. context.md is injected into the model at session start. If you commit .recall/ as shared team memory , treat it like any other shared input: a teammate (or a bad actor with repo write access) could craft a context.md to attempt prompt-injection. SessionStart fences the content and labels it untrusted data, and Claude asks before relying on it — but if you don't fully trust who can write the repo, keep .recall/ git-ignored (the default). Committing .recall/ Both are fine. Commit it for shared team memory, or git-ignore it for personal memory ( .gitignore ships ignoring it by default — flip the comment to commit). Install From the marketplace (this repo is its own marketplace): /plugin marketplace add raiyanyahya/rec