Total Agent Memory

Search knowledge by tag. Returns all active records with matching tag (partial match). Useful for categorical browsing.

v11.0: like memory_recall but with rerank=False, diverse=False forced. Deterministic fast path — zero LLM, FastEmbed-only.

Self-assessment: how competent am I in given domains? Shows level, confidence, blind spots.

Find skills matching a trigger. Skills are learned procedures — HOW to do things.

Record skill usage or refine a skill. Updates success rate and metrics.

Memory statistics with health metrics: sessions, knowledge by type/project, retention zones (active/archived/consolidated), stale records, storage size, config, write path (embedding backfill queue, outbox intents, swallowed errors by component over 24h, importance budget clamps).

v11.0 W1-C: deterministic temporal reasoning — Allen interval relations, duration arithmetic (days/weeks/months/years), and natural-language date normalization (en + ru). Pass op=relation|duration_between|normalize.

Browse session history. sessions_ago=N for 'N sessions ago', session_number=1 for first session, date_from/date_to for date ranges.

Update existing knowledge. Replaces the record `id`, or the best match for `find` (within `project` when given): supersedes it and creates a new version.

v11.0: pre-load FastEmbed model and open the vector store, so the first save/search after process start doesn't pay model-load latency.

v10 — Render the per-project wiki digest (top decisions, active solutions, conventions, recent changes) as Markdown. Pass `project` to refresh one wiki, omit it to refresh all active projects. Files land in <MEMORY_DIR>/wikis/<project>.md and are deterministic (no LLM call).

v8.0: advance a task to the next phase.

Attach or remove a phase scope on a rule (v8.0 lazy rule loading). Tag-based: manages 'phase:<X>' on the rule's tags. phase=null clears the phase tag (rule becomes core — applies to every phase). Valid phases: van, plan, creative, build, reflect, archive.

v8.0: save a structured architectural decision (options + criteria matrix + rationale + discarded). Adds `structured` tag and a JSON blob in context. Use for Creative-phase outputs; plain type=decision memory_save still works.

Persist one user prompt into the `intents` table (same source as the UserPromptSubmit hook). Use when programmatically seeding intents — the hook covers normal interactive usage. Dedupes same prompt within 5 min per session.

Substring search over user prompts (LIKE). Returns newest match first. Useful for 'what did I ask about X' without mining transcripts.

Log an error/failure for pattern analysis. Call AUTOMATICALLY when: bash command fails, wrong assumption discovered, API returns error, config issue found, loop detected, or any mistake occurs. System detects patterns (3+ same category) and suggests insights.

Manage insights from error patterns (ExpeL-style). Actions: add (create, importance=2), upvote (+1), downvote (-1, auto-archive at 0), edit, list, promote (to rule when importance>=5 AND confidence>=0.8). Call 'add' when pattern detected. Call 'upvote' when insight confirmed again.

Analyze error patterns and self-improvement stats. Views: error_patterns (frequency, repeating 3+), insight_candidates (ready for promotion), rule_effectiveness (success rates, stale rules), improvement_trend (weekly errors), full_report (all). Call periodically to track improvement.

Save a verbal self-reflection (Reflexion pattern). Call after completing a task or encountering difficulty. NOT for errors (use self_error_log). For meta-observations about strategy, approach effectiveness, process improvements.

Manage behavioral rules (SOUL). Rules are promoted insights that shape agent behavior. Actions: list, fire (record relevance), rate (success=true/false), suspend, activate, retire, add_manual, followed (surface_id from self_rules_context(query=...): was the rule followed?), report (follow-rate effectiveness with Wilson CIs, measurement only). success_rate = success / (success + fail). Auto-suspend: 5+ ratings and the 95% upper bound of success_rate < 0.4.

Get active behavioral rules for current session. Call at SESSION START to load rules. Returns rules filtered by project and scope. v8.0: pass `phase` to lazy-load rules relevant to current task phase — core rules (no phase tag) + rules tagged phase:<X>. Cuts prompt tokens ~70%. After task completion, rate rules: self_rules(action='rate', id=X, success=true/false).

End-of-session capture: summary + highlights + pitfalls + next_steps so the next session can resume cleanly. Set auto_compress=true to have the LLM generate the missing summary/next_steps/pitfalls from stored session artifacts (or from an optional `transcript`).

At session start: return the most recent unconsumed end-of-session summary with highlights / pitfalls / next_steps.

v8.0: start a task in `van` phase (auto-classifies level if missing).

v8.0: list all phases of a task in chronological order.

Record a learned workflow (named sequence of steps) for future reuse.

Predict outcome (success probability, avg duration) for a workflow by id OR by trigger keyword. Uses Laplace-smoothed success rate.

Record a workflow execution outcome. Outcome ∈ {success|failure|partial|aborted}. Aggregates update automatically.