Архитектура долгосрочной памяти для ИИ-агентов. Echo Memory создана, чтобы запоминать всё, что агент когда-либо узнал, наилучшим возможным способом, и продолжать эффективно извлекать и записывать эту память независимо от того, сколько истории накопилось, — для инструментов разработки, чат-ботов, DevOps-агентов или любой другой агентной системы, локальной или развернутой.
Каждый ИИ-агент начинает с нуля, если только что-то не запомнило, что произошло в прошлый раз, и не запомнило это достаточно хорошо и достаточно быстро, чтобы оставаться полезным спустя месяцы или годы накопленной истории. Большинство инструментов памяти решают задачу краткосрочного запоминания с помощью обычного векторного поиска по сохранённым фактам. Это деградирует по мере роста истории: больше кандидатов, больше шума, медленнее извлечение. Echo Memory построена вокруг алгоритма чтения/записи и структуры данных, которые продолжают работать на длинных горизонтах, а не только в первый день:
Временной, самоуплотняющийся граф памяти. Факты — это рёбра между сущностями, а не плоские векторные строки. Старая, редко используемая память не просто накапливается: со временем она консолидируется в обобщения более высокого уровня (никогда не удаляется, всегда можно проследить до оригинала), поэтому стоимость извлечения остаётся ограниченной тем, что актуально сейчас, а не тем, что когда-либо было записано. См. docs/designs/echo-memory-design.md для описания реального механизма.
Настоящая структура графа, а не только сходство. Многошаговые запросы, например «как мы сюда попали?», выполнимы, потому что факты связаны, а не просто индивидуально встроены.
Причинная типизация, а не только сходство. Рёбра могут быть помечены как caused_by, led_to, blocked_by, contradicts, заданные самим агентом на основе прочтения разговора, а не выведенные статистически. Честно о том, что осуществимо сегодня, а что нет.
Аудируемость по дизайну. Каждое изменение памяти логируется с пояснением на простом языке, которое можно прочитать (echo-memory why <fact_id>). Память, которая консолидируется и редактирует себя, заслуживает доверия только если видно, почему.
Один движок хранения для любого масштаба. Postgres + pgvector + Apache AGE, от одного локального агента до общеорганизационного общего графа, охватывающего всех агентов, которых запускает бизнес. Никакой принудительной миграции позже. (Новизна — в структуре памяти и алгоритме, работающих поверх Postgres, а не в новом движке базы данных; см. дизайн-документ, почему.)
Любой агент, а не один вендор. Интерфейс — MCP: любой MCP-совместимый агент может читать и записывать в тот же граф памяти, будь то ассистент для программирования, чат-бот, операционный агент или что-то созданное внутри компании.
Related MCP server: smriti-memcore
Разработчик, запускающий локальных агентов, который хочет, чтобы Claude Code, Cursor или что-то ещё перестало терять контекст между сессиями и инструментами.
Команда или организация, запускающая агентные системы в продакшене (боты поддержки, DevOps-агенты, внутренние инструменты), которой нужен общий слой памяти вместо N разрозненных, с моделью аренды (ниже), чтобы правильно ограничивать доступ для каждого агента, команды или всей организации.
Ранняя и поэтапная стадия. См. docs/designs/ для полной архитектуры и плана сборки v1a → v1b. Проверенный клин, движущий v1a, — это именно кросс-инструментальная память агентов для программирования (ежедневная боль основателя, реальная и протестированная). Более широкое видение выше — это цель, к которой строится эта архитектура, а не то, что доказывает сама v1a. v1a доказывает базовое извлечение, прежде чем v1b добавит причинную типизацию и многошаговое извлечение из графа, а до v1.1 добавит общеорганизационную аренду, от которой зависит более широкое видение.
Пока не готово к использованию; см. docs/designs/echo-memory-design.md для текущего плана сборки и прогресса, и docs/DEVELOPMENT.md для локальной настройки, когда появится код.
Хранилище: PostgreSQL с расширениями pgvector и Apache AGE
Извлечение: гибридный векторный + полнотекстовый поиск (v1a), с Personalized PageRank через networkx, добавленным в v1b для многошагового ассоциативного извлечения
Интерфейс: сервер Model Context Protocol: write_episode, query_memory, get_audit_log
См. CONTRIBUTING.md. Приветствуются issues и PR; пожалуйста, сначала прочитайте дизайн-документы, чтобы предложения соответствовали поэтапному плану сборки.
Apache License 2.0. См. LICENSE.
Human-readable audit trail: what was written, invalidated, superseded, or resolved, and why. since is an ISO8601 timestamp; entries at or after it, chronologically ordered.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | ||
| since | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden for behavioral disclosure. It usefully explains that results are chronological, filtered by 'since', and cover certain event types. However, it does not disclose pagination, response shape, or the behavior when 'since' is null.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is tight and front-loaded, with the core purpose stated first and the 'since' behavior in the second sentence. It wastes no words, though the missing scope explanation prevents a top score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description leaves important gaps: it does not define the required 'scope' parameter, describe the return structure, or state how 'since' defaults behave. The event-type list is helpful but only partially completes the picture.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It clearly documents the 'since' parameter as an ISO8601 timestamp with ordering semantics, but it does not explain the meaning of the required 'scope' parameter at all, leaving a significant gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies the tool as a human-readable audit trail and lists the event categories it covers (written, invalidated, superseded, resolved) plus the rationale. This distinguishes it from the sibling memory operations, though it lacks an explicit retrieval verb like 'gets' or 'returns'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is for viewing historical audit information but gives no explicit guidance on when to choose this over write_episode, query_memory, or record_recall_save. There are no stated exclusions, prerequisites, or alternative routing conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recall prior facts relevant to query, from this agent's own memory (scope="solo") or the pool shared across this user's agents (scope="shared"). Call this at session start, and any other time recalling prior context would save the user from re-explaining something - check here before asking them to repeat themselves or guessing at context you don't have.
digest=True ignores query and returns the most recently written active facts instead, as an opt-in "catch me up" convenience; call it explicitly at session start if you want one, it's never automatic.
A pending_ingest field appears when memory files have been written that
the graph hasn't heard about yet. Read each listed file and call
write_episode with the entities and facts it states, then mark it done
with echo-memory pending --done <path>. The queue exists because
extraction needs a model and this server never calls one.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| scope | Yes | ||
| top_k | No | ||
| digest | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that digest=True ignores the query, returns the most recently written active facts, and is never automatic. It also reveals the pending_ingest field behavior and why the queue exists, which is valuable operational context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the main purpose, then usage, then digest, then the pending_ingest workflow. Each paragraph is relevant and non-redundant; the length is justified by the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, usage timing, scope semantics, digest behavior, and the pending_ingest workflow. It is less complete on the output format of ordinary recall results and top_k semantics, which matters more because there is no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, so the description must compensate. It explains scope values ('solo' vs 'shared') and the digest parameter's behavior in detail. However, top_k is never mentioned, and the behavior of a null query without digest is left unspecified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Recall prior facts relevant to query' from memory. It immediately clarifies the two scopes ('solo' vs 'shared'), making the tool's function unmistakable and distinct from write-oriented siblings like write_episode.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is explicitly prescribed: 'Call this at session start, and any other time recalling prior context would save the user from re-explaining something.' It also tells the agent to check here before asking the user to repeat themselves, and it explains when digest should be invoked explicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record that a fact you recalled from memory saved the user from re-explaining something to you.
Call this IN THE SAME TURN, the moment it happens. The trigger is concrete: you called query_memory (or read a memory-derived fact), it answered something the user would otherwise have had to tell you again, and the fact was originally written by a DIFFERENT tool or a past session.
That last part is the whole point, and it is why this takes fact_id
rather than a written_by string. Pass the fact_id of the fact that
helped - every query_memory result carries one. The server reads that
edge's own agent_id and uses it as written_by; the caller does not get
to assert who wrote a fact.
Until 2026-08-29 written_by was free text supplied by the caller. Nothing
checked the fact existed, so the number gating v1a was a string typed by
the model being graded. A fact_id is checkable, so the reading is
admissible.
recalled_by is you, defaulting to this server's own agent id. If the fact's author and you are the same tool, the save is still recorded but does not count toward the trial's bar - recalling your own note from ten minutes ago is not the thing being measured.
note should be one sentence naming what it saved re-explaining, written so it still makes sense read cold in six months. Recording the identical note twice is a no-op, so a retry after an error is safe.
Do NOT call this speculatively, for a fact you wrote this session, or because a recall was merely interesting. It is evidence for a gate that decides real build work; an inflated count is worse than an empty one.
| Name | Required | Description | Default |
|---|---|---|---|
| note | Yes | ||
| scope | Yes | ||
| fact_id | Yes | ||
| recalled_by | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and handles it thoroughly. It discloses idempotency (duplicate note is a no-op), disqualification (same-tool recalls are recorded but do not count), server-side written_by resolution, and the consequences of inflated counts. It also warns that the caller cannot assert authorship.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core action and trigger, then organized into focused paragraphs. It is long, but the behavior is subtle enough to justify the length. The historical note about v1a is arguably redundant for callers, but it does explain why fact_id is required.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is unusually complete for a recording tool: it explains when, why, and how to call it, including edge cases and disqualifying conditions. It falls short of a 5 only because the required `scope` parameter remains undocumented and success/error behavior is not explicitly described beyond the duplicate no-op.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context for fact_id, note, and recalled_by, going well beyond the bare schema. However, schema coverage is 0% and the required `scope` parameter is never explained, leaving a significant gap in a required field.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Record that a fact you recalled from memory saved the user from re-explaining something to you.' This clearly distinguishes it from siblings like query_memory (which reads memory) and write_episode (which writes memory) by positioning it as a post-recall evidence-recording action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives an explicit trigger condition: call in the same turn, only when query_memory returned a memory-derived fact that would otherwise require re-explanation, and only when the fact was written by another tool or past session. It also lists clear exclusions: do not call speculatively, for facts written this session, or simply because the recall was interesting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record something worth remembering later: a decision, a correction, a stated preference, or context that would otherwise have to be re-explained to a different tool or a future session. Call this proactively and immediately when you notice one of these - don't wait to be asked, and don't batch it up for later in the conversation. The cost of a missed memory (re-explaining something later) is higher than the cost of one extra call.
You (the calling agent) extract entities/facts yourself - this server never calls an LLM. Exact shape, every key required unless marked optional:
entities: [{"name": "Postgres", "type": "tool"}, ...]
name: non-empty string, unique per entity in this call
type: any short string describing what kind of thing this is (e.g. "tool", "person", "decision", "preference") - your choice, not a fixed enum
facts: [{"source": "Decision", "target": "Postgres", "relation_type": "uses", "fact": "decided to use Postgres for storage", "confidence": "extracted"}, ...]
source/target: must each exactly match a "name" in entities above
relation_type: any short string describing the relationship (e.g. "uses", "prefers", "caused_by") - your choice, not a fixed enum
fact: the actual sentence to remember, plain text
confidence: MUST be exactly one of "extracted" (directly stated), "inferred" (you deduced it), or "ambiguous" (uncertain) - any other value, including numbers or omitting it, is rejected
entity_resolutions (optional): only needed when a previous call returned ambiguous_entities and you're now confirming which candidate a mention refers to, or that it's new: {"mention name": {"resolved_to": "" | "new"}}. Omit entirely on a call with no prior ambiguity to resolve.
Example call: write_episode(scope="solo", session_id="sess-1", entities=[{"name": "Postgres", "type": "tool"}, {"name": "Decision", "type": "decision"}], facts=[{"source": "Decision", "target": "Postgres", "relation_type": "uses", "fact": "decided to use Postgres for storage", "confidence": "extracted"}])
| Name | Required | Description | Default |
|---|---|---|---|
| facts | Yes | ||
| scope | Yes | ||
| entities | Yes | ||
| session_id | Yes | ||
| entity_resolutions | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and meets it thoroughly. It discloses that the server never calls an LLM and that the calling agent must extract entities/facts itself, specifies that the confidence value must be exactly one of three literal strings or the call is rejected, and explains when entity_resolutions is required. It also documents the strict matching constraint between fact source/target and entity names, giving the agent a clear behavioral model.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but every sentence earns its place: it front-loads the purpose, gives precise field-by-field shapes and validation rules, and ends with a concrete example. Given that the schema provides no property descriptions, the length is justified and well-structured rather than verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter tool with no annotations, no output schema, and an empty schema, the description covers the entities/facts structure, confidence validation, optional entity_resolutions flow, and an example. It falls short on the semantics of scope and session_id, and it does not describe what the tool returns in response, so an agent still has some uncertainty about the complete call contract.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema is nearly empty (objects with additionalProperties: true and 0% description coverage), so the description must compensate. It richly defines entities (name, type, uniqueness), facts (source/target/relation_type/fact/confidence with validation), and entity_resolutions (resolved_to or new). However, the two required parameters scope and session_id are only shown in the example call and never semantically defined, leaving a gap in compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb and resource: 'Record something worth remembering later' and enumerates concrete examples (a decision, a correction, a stated preference, or context). It does not explicitly contrast itself with the sibling tool 'record_recall_save', so an agent cannot immediately distinguish between the two write-like tools, which prevents a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit situational triggers: 'Call this proactively and immediately when you notice one of these - don't wait to be asked, and don't batch it up for later in the conversation.' It also explains the cost-benefit rationale for erring on the side of calling. However, it does not mention any alternatives or state when not to use the tool, so it lacks exclusions and sibling routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_audit_logquery_memoryrecord_recall_savewrite_episodewrite_episode creates new memory, query_memory retrieves it, get_audit_log inspects history, and record_recall_save logs a specific recall-save event. Even the two 'record' tools are cleanly separated by what they write: episode facts versus a recall-save reference.
All four tools follow the same imperative verb_snake_case convention: write_episode, query_memory, get_audit_log, record_recall_save. There is no mixing of camelCase or inconsistent verb styles.
Four tools is well-scoped for a memory server: a write path, a query path, a history/audit path, and a meta-tracking path. No tool feels redundant, and none is missing for the stated purpose.
The core write-query-audit loop is covered, and agents can work around stale facts by writing corrections. The main gaps are the lack of an explicit invalidate/delete tool and the fact that completing the pending-ingest workflow requires an external CLI command, but these are minor rather than fatal.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Long-term memory for AI agents: durable records, observable retrieval, governed context assembly.
Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ayushcodes10/echo-mem'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
