> ## Documentation Index
> Fetch the complete documentation index at: https://docs.myrmagent.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Dialectic Profiling

> Async Cognitive Deriver extracts communication style, decision habits, and implicit goals — not regex guessing.

# Dialectic Profiling (Cognitive Deriver)

Myrm replaces brittle regex-based preference extraction with an **async Cognitive Deriver**: after a conversation ends, a background LLM pass performs dialectic reasoning over the exchange and writes structured profile entries into memory.

## What gets inferred

| Dimension               | Examples stored as profile memory                           |
| ----------------------- | ----------------------------------------------------------- |
| **Communication style** | Concise vs verbose, formal vs casual, language mix          |
| **Decision logic**      | Risk tolerance, prefers options vs direct recommendation    |
| **Implicit goals**      | Ongoing projects, unstated priorities surfaced from context |

Evidence-backed only: if the model cannot cite clear signals, fields stay empty (anti-hallucination).

## How it works (runtime)

1. **Extraction** — `MemoryExtractor` prompts include a dialectic section; conclusions land as `memory_type="profile"` with high confidence when supported.
2. **Deriver cycle** — `cognitive/deriver.py` runs async dialectic reasoning on recent messages and updates vector + graph evidence.
   * **Token-Aware Sliding Window**: Automatically limits input messages to \~16,000 characters before sending to the LLM to prevent OOM errors and save budget.
   * **Dual-Write Degradation**: Securely dual-writes to GraphStore and SemanticMemory; if the graph backend fails or is disabled, gracefully degrades to SemanticMemory without losing data.
3. **Taste Summary** — `compile_taste_summary` consolidates active semantic/profile rows into a fast-read summary for the system prompt.
4. **Injection** — `MemoryContextMiddleware` injects taste summary **before** each turn (no extra tool round-trip vs Honcho-style `honcho_context` calls).
5. **SSE Noise Reduction** — UI only notifies you when a **disruptive** change (contradict/supersede) occurs; standard preferences are extracted entirely silently in the background.
6. **GUI** — `TasteSummaryCard` shows badges; users can edit or remove inferred traits in the Memory Command Center.

## vs Honcho / Mem0-style SaaS

| Aspect                     | Typical memory SaaS                    | Myrm                                                                  |
| -------------------------- | -------------------------------------- | --------------------------------------------------------------------- |
| Preference extraction      | Observation → representation pipelines | **Cognitive Deriver** after chat, LLM dialectic                       |
| Context assembly           | Agent calls a memory tool per turn     | **Automatic** middleware injection                                    |
| Management                 | Often CLI-only                         | **GUI** browse, approve, audit, rollback                              |
| “Dream” long-horizon goals | Separate expensive pipeline            | **Zero extra pipeline** — goals folded into taste summary maintenance |

## Related docs

* [Memory System](/docs/core-concepts/memory-system) — 8 memory types, retrieval, forgetting
* [Product Architecture](/docs/getting-started/product-architecture) — harness vs server vs UI layers

For competitive positioning detail, see internal materials `MEMORY_ADVANTAGE.md` (§ vs Honcho / Mem0).