Hindsight Coding-Agent Memory

This machine runs the hindsight-coding-agents plugin: long-term project memory for coding sessions, backed by a Hindsight server. You (the agent) are already wired into it — this skill explains what happens automatically, which tools you have, and how to configure or debug it.

What happens automatically (no action needed)

• Per-repo memory bank: each repository resolves to a bank (shown in the session banner: ↳ memory bank “coding-agent::<repo>”). Worktrees share the main repo's bank.
• Ingestion builds itself: on first open, the bank is seeded from recent commit messages and a read-only codebase survey; every session start, a background engine tops it up (new commits, new conversations) and keeps 5 knowledge pages current. There is NO ingest command to run.
• Session synthesis: by default, the first prompt of a session triggers one deep memory synthesis (reflect) injected into context. With autoReflect=false, the agent searches the knowledge pages first and reflects only when they are too shallow.
• Write-back: the session transcript is retained into the bank automatically at session end (per-turn on opencode). The user never needs to "save" a conversation.

Storing things deliberately

When the user says "store this in hindsight" / "remember this":

• The current conversation is captured automatically at session end — say so; no tool needed.
• An external document, notes, or durable findings → hindsight_ingest_document(title, content).
• A new feature/initiative being started → hindsight_capture_initiative(title, summary), right after the plan is agreed and before code is written.
• A plan that materially changed (goal, scope, or rationale — including mid-implementation) → call hindsight_capture_initiative again with relates_to_page_id set to that initiative's page id, summarising the current intent. Same page, updated plan — never a second page. Trivial course-corrections don't count.

Retrieving

• hindsight_search_knowledge_pages(query) — FIRST STOP for project questions (components, conventions, past decisions, initiatives). Server-side hybrid search, fast.
• hindsight_read_knowledge_page(page_id) / hindsight_list_knowledge_pages — read pages fully.
• hindsight_reflect(query) — deep reasoning over the whole memory for WHY questions and exact decided values; slower (seconds), use deliberately.
• Credit visibly whenever memory informs an answer: start that part with 🧠 From Hindsight memory (<page>): … — and never credit memory that didn't contribute.

Correcting wrong or stale memory

If you verify that something Hindsight served is wrong or outdated (the code, git, or an external source contradicts it), FIX THE RECORD — don't just ignore it. Call hindsight_ingest_document with:

• title: Correction: <topic> (e.g. Correction: retry policy 4xx set)
• content: (1) what memory claimed, (2) what is verifiably true now, (3) the evidence you checked (file/commit/output). Quote exact values verbatim.

Newer facts supersede older ones in retrieval, so one clear correction permanently outranks the stale memory. Do this whenever you catch a wrong injected memory, a stale knowledge-page claim, or an outdated decision — silent disregard leaves the trap armed for the next session.

Install / update

npx @vectorize-io/hindsight-coding-agents install all          # every detected agent, wired natively
npx @vectorize-io/hindsight-coding-agents install claude-code  # or just one
npx @vectorize-io/hindsight-coding-agents uninstall all        # removes exactly what install added

install takes an explicit target — all, or one or more harness names. A bare npx @vectorize-io/hindsight-coding-agents install changes nothing and prints the choice, so wiring every agent on the machine is never something that happens by accident. Updating is the same install command again — it re-copies the runtime in place.

Local daemon settings (daemon mode)

Daemon settings keep the names the old per-agent Claude Code plugin used, so an existing environment carries over unchanged:

Any HINDSIGHT_API_* variable you export is forwarded to the daemon, so server-side settings need no equivalent here.

Configuration

Configuration is one JSON file: ~/.hindsight/coding-agent.json. Layering, later wins per field:

1. built-in defaults
2. environment variables — HINDSIGHT_API_URL, HINDSIGHT_API_TOKEN, and one per scalar setting (HINDSIGHT_<FIELD_IN_CAPS>), for containers and CI that inject config rather than write a file
3. the file's top level
4. its harnesses.<name> section — per-agent override
5. its banks.<resolvedBankId> section — per-repo override, applied after the bank is resolved (see Per-repo opt-in/out)

Environment variables are a fallback: the file wins wherever it sets a value, so adding env to an existing setup changes nothing. The two list-valued settings, retainTags and optInPaths, take a comma-separated value (HINDSIGHT_RETAIN_TAGS="project:{gitProject},env:work"); entries are trimmed and blanks dropped. The map-valued settings (mapPathToBank, harnesses, banks, retainMetadata) are file-only — per-key branching doesn't survive flattening into one variable. maxParallelRetains is available as HINDSIGHT_MAX_PARALLEL_RETAINS for containers and CI.

HINDSIGHT_CONFIG moves the file itself — point it at another path for a container or a test harness where $HOME is not the right anchor. It is still exactly one file; only its location changes. (The other variables that are not settings are HINDSIGHT_LOG_FILE, HINDSIGHT_DIAG_FILE and HINDSIGHT_LOG_LEVEL — see Diagnostics & logging.)

When a change takes effect

Config is read when a process starts — the file is not watched — so when an edit applies depends on what reads it:

apiToken is the exception. Every host re-reads it when the server rejects a request, so enabling authentication or rotating the key is picked up on the next call with nothing to restart — otherwise a rotation would leave a long-running agent failing every memory call until it was restarted. Everything else follows the table: apiUrl, disabled, bank routing, gitIngest, and the survey and knowledge-page settings.

hindsight_diagnose reports both sides of that gap — what the file says now, and what the running client is actually using.

Opt-in only

By default every project gets memory — that is what makes the plugin zero-setup. If you would rather nothing be remembered until you say so, turn memory off everywhere and name the projects that may use it:

{
  "optInOnly": true,
  "optInPaths": ["~/work/client-x", "~/oss"],
}

Anything outside those paths is inert: no bank is created, nothing is retained, no seed runs, and the agent behaves exactly as it would without the plugin. Approving costs nothing else — optInPaths says which projects, not which bank, so an approved repo keeps its usual coding-agent::{gitProject} name. Paths are prefixes, so approving ~/work approves every repo under it while each still gets its own bank.

A mapPathToBank entry counts as opted in too, since routing a path to a named bank already declares that project. A bare bankId does not: it names a bank rather than a project, so it cannot say which work may be remembered, and a privacy switch has to fail closed.

There is no per-repo opt-in file, for the same reason there is no repo-carried config at all: a cloned repository must not be able to turn memory on.

There is deliberately no repo-carried config file — per-repo bank routing is mapPathToBank, per-agent differences are harnesses.<name>.

Each entry point knows which harness it is (the opencode plugin is loaded by opencode, the codex hook by Codex...), so one shared config serves several agents side by side:

{
  "apiUrl": "https://api.hindsight.vectorize.io",
  "harnesses": {
    "opencode": { "reflectTimeoutMs": 60000 },
    "claude-code": { "disabled": true }, // e.g. memory off for Claude only
  },
}

Reference

pageTriggerType/pageTriggerCron decide only when a page refreshes. How it refreshes belongs to the server: Hindsight creates a knowledge page with a delta refresh (each pass edits the page instead of rebuilding it) that doesn't reflect over sibling pages, and these settings merge over those defaults rather than replacing them.

These settings apply to pages created from here on. Changing them does not migrate the pages a repo already has: a page keeps the trigger it was created with, so a bank seeded before you set "manual" keeps refreshing on every consolidation. To move an existing page, change its trigger through the API (PATCH /knowledge-base/nodes/{id}), an SDK, or the control plane — or delete it and let the next session seed it again.

Per-repo opt-in/out — banks.<bankId>

Per-repo control lives in the SAME file, keyed by the resolved bank id (shown in the session banner) and applied AFTER bank resolution — so it works regardless of where the repo lives, and survives directory moves:

{
  "banks": {
    "coding-agent::secret-client": { "disabled": true }, // blacklist: no memory at all
    "coding-agent::old-name": { "bank": "team::shared" }, // rename / converge banks
    "coding-agent::big-mono": { "gitIngest": "full", "retainSessions": false },
  },
}

Any behavioral field can be overridden per bank, and bank renames the destination (single hop: the section is selected by the resolved id, the target is literal — several ids may converge on one shared bank, and the target's own section is not consulted). Other bank-resolution fields are ignored inside a bank section.

Recipe: two repos, one shared bank

Two ways, by what the natural key is:

By resolved id — you know the repo names; works wherever the repos live (and keeps working if they move). Both ids converge on one literal target:

{
  "banks": {
    "coding-agent::backend": { "bank": "team::product" },
    "coding-agent::frontend": { "bank": "team::product" },
  },
}

By path prefix — the repos live under one directory; a single mapPathToBank entry covers every repo (present and future) beneath it:

{
  "mapPathToBank": { "/Users/me/work/client-x": "client-x-memory" },
}

Rule of thumb: converge by id for a hand-picked set of repos; map by path when a folder is the boundary ("everything I clone under work/client-x shares memory").

Bank resolution

Coding memory is per repository. Resolution order for the working directory:

1. mapPathToBank — longest matching absolute-path prefix (mapping a repo root covers every subdirectory; deeper mappings win; overrides even an explicit bankId).
2. Static — bankId set (or dynamicBankId: false).
3. Dynamic — bankIdTemplate with placeholders:
   • {gitProject} — worktree-aware repo name: git rev-parse --git-common-dir resolves every linked worktree to the main worktree's basename, so all worktrees of a repo share one bank (bare repos use the bare dir name). Outside a repo there is nothing for git to resolve, so it falls back to the basename of the directory the session started in — an agent that cds into a subdirectory keeps writing to one bank, and a subdirectory gets its own bank only when you deliberately start a session there
   • {project} — plain working-directory basename
   • {harness} — the entry point asking (opencode, claude-code, codex, antigravity-cli, cursor-cli, copilot-cli)
   • {channel} / {user} — $HINDSIGHT_CHANNEL_ID / $HINDSIGHT_USER_ID

The default "coding-agent::{gitProject}" is harness-neutral, so opencode, Claude Code, and Codex all share one memory per repo — use "{harness}-{gitProject}" to split per agent instead.

Recording where a memory came from

With a bank per repo, the bank is the answer to "where did this come from". On a deliberately shared bank — one bank holding cross-project knowledge so facts recall everywhere — it isn't: every memory looks alike. retainTags and retainMetadata stamp that provenance onto conversations, git history and diffs, survey lifecycle documents, initiative markers, and documents saved through hindsight_ingest_document:

{
  "bankId": "shared", // one bank for everything
  "retainTags": ["project:{gitProject}", "env:work"],
  "retainMetadata": { "repo": "{gitProject}" },
}

Recalls can then filter by project:<repo>, and every document shows which repository it came out of. Both accept the same placeholders as bankIdTemplate — {gitProject}, {project}, {harness}, {channel}, {user} — plus {bankId}, {sessionId} and {timestamp}. {gitProject} is worktree-aware here too, so every linked worktree of a repo stamps one name. {sessionId} resolves to unknown for documents that do not originate from an agent session.

The plugin's own source: and harness: tags are reserved: entries in those namespaces are ignored with a warning, so a document's agent attribution always reflects the agent that actually wrote it.

One set of beliefs per repo

Every document this integration writes carries provenance tags — source:chat, harness:<id>, knowledge:<kind>, plus anything from retainTags. Those tags say who wrote a memory; they are what filters recall and draws each document's agent logo, and they stay on the facts.

They are not, however, a good boundary for observations. Consolidation's own default (combined) builds one observation set per distinct tag set, so the same repository worked on by two agents would grow two parallel sets of beliefs — one per harness — that never merge, each blind to the other, at double the consolidation cost. Which agent happened to be typing does not change whether a convention or a decision is true.

So the integration retains with observationScopes: "shared": one global, untagged observation scope per bank, which is what a bank already is — one project's memory. Set the field to change it:

{
  "observationScopes": "combined", // one observation set per distinct tag set (server default)
  "banks": {
    "coding-agent::mono": { "observationScopes": "per_tag" }, // per-repo, like any behavioral field
  },
}

"per_tag" and "all_combinations" split further still, and an explicit [["project:demo"], …] declares the scopes literally. HINDSIGHT_OBSERVATION_SCOPES sets the scalar modes; a scope list is file-only. Changing this does not rewrite observations already consolidated under the old scoping — they stay where they were built, and new work accrues under the new setting.

Diagnostics & logging

Two files, two audiences:

Leveled plugin log (humans debugging): $TMPDIR/hindsight-coding-agent/plugin.log (override HINDSIGHT_LOG_FILE) — timestamped LEVEL [scope] message lines from every component, including the ingestion engine. Level defaults to info; set "logLevel": "debug" in config or HINDSIGHT_LOG_LEVEL=debug for ad-hoc debugging (at debug, every diag event below is mirrored here too, so one file tells the whole story).

Structured diag events (machines/harnesses): every reflect and page-fetch outcome is appended as a JSON line to /tmp/hindsight-plugin.log (override with HINDSIGHT_DIAG_FILE):

{
  "ts": "2026-07-27T07:05:52Z",
  "harness": "claude-code",
  "event": "reflect_ok",
  "ms": 14210,
  "chars": 792,
  "query": "..."
}

reflect_failed / pages_failed record the error; if you're comparing memory-on vs memory-off, check this file — a run whose reflects failed is a no-memory run. Seed starts are logged as seed_started.

Is the memory ready yet?

hindsight_sync_status — the agent-facing tool, dist/status.js for scripts — answers exactly that: "synced": true means the seeded memory is queryable. It also reports gitlog freshness, how far per-commit deepening has got, the codebase survey's state (surveyBaseline is the HEAD the last survey started from, surveyDocs counts the findings documents that have landed, 0–4 — a baseline with no findings retries automatically), and the extraction operations still in flight.

Resetting a repo's memory

Delete its bank on the server. The bank is the only state this integration keeps, so the next session in that repo is a true first open — seed and survey run again from scratch. There are no client-side files to clean up.

Marker documents you may notice

Two document ids exist for the machinery's own bookkeeping. Both are safe to ignore and safe to delete:

• survey-baseline:<sha> — reads "🛰️ researching…" while a codebase survey runs and flips to "✅ completed" once its findings land. It is retained under the survey strategy, whose marker rule extracts nothing from a status marker, and it drives the re-survey cadence (surveyRefreshCommits) and surveyBaseline in sync status.
• gitlog:<repo> — the aggregated commit-message seed document, re-upserted rather than duplicated when the seed runs again.

When memory seems to be missing

Failures never break the agent: a reflect, page fetch or retain that fails degrades to an ordinary memoryless turn and is recorded in the logs. "No memory" is therefore a log question — check the diag file for whether session_start and deepen_started ever fired for that bank. A session that was already running when the plugin was installed has no SessionStart behind it; its first prompt after the install self-heals.