1. Conduid
  2. Blockchain
  3. PseudoLife Memory
MCP server · Blockchain

PseudoLife Memory

Persistent long-term memory for Claude: memory bank, fact cortex, dream consolidation, graph.

Unclaimed blockchain
37Low

Scored 3 months ago · breakdown

About PseudoLife Memory

PseudoLife Memory is an MCP server published by Pseudogiant-xr in the Blockchain category: persistent long-term memory for Claude: memory bank, fact cortex, dream consolidation, graph.

The repository has 6 stars and 1 forks, with the last commit 7 hours ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

uvx
uvx pseudolife-mcp
pip
pip install pseudolife-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (30)

document_ingest(path, source?)Index a file (txt/md/pdf/html) verbatim in the reference bank — the lossless complement to agent-side distillation ([division of labor](docs/guide/memory-model.md#background-documents--the-reference-bank))

Parameters not published.

document_search(query, top_k?)RAG search over the reference bank only

Parameters not published.

memory_agents(action, project?, task?, status?)Experimental, opt-in peer awareness or update of the caller's registered context; unknown episode scope stays unknown, and activity is not a resource reservation

Parameters not published.

memory_alias(entity, alias)Bind an alternative name — lookups resolve aliases first

Parameters not published.

memory_consolidate(replaces?, new_text, source?, tags?, entry_ids?)Replace selected entries with one canonical note; validate every ID (or unique exact text) before any changes

Parameters not published.

memory_consolidation_candidates(query?, episode?, ...)Cluster near-duplicate memories ripe for consolidation

Parameters not published.

memory_dream(action, limit?, commit_token?, apply?, snippets?, run_id?)Drive the dream: `status` / `pull` / `commit` / `run` (server-side extractor) / `runs` (audit trail of recent passes) / `rollback` (revert the latest committed pass from its pre-image journal) / `deep` (full-corpus graph consolidation; dry-run unless `apply`, which snapshots the graph tables first; `snippets=false` omits candidate evidence; responses carry evidence-enriched `merge_proposals` for near-duplicate triage)

Parameters not published.

memory_episode_summary(id)Stats + tag/source distribution + recent entries within an episode

Parameters not published.

memory_fact_get(entity, attribute)The one CURRENT canonical value at a slot (+ parked contenders); on an empty slot returns ranked `candidates` (same-entity, then similar slots); aged/contested facts carry a ready-made `correct_with` call (as do `memory_search` / `memory_world_search` hits)

Parameters not published.

memory_fact_resolve(entity, attribute, accept)Settle a contested slot — adopt (`true`) or discard (`false`) the contender

Parameters not published.

Show all 30 tools
memory_fact_set(entity, attribute, value, origin?, confidence?, episode?, freshness_class?, authority?, distortion_tolerance?)Assert a canonical fact deliberately (insert / confirm / supersede / contest); `freshness_class` (`auto` default) says how fast the slot rots — `auto` infers it from the entity's kind; `authority`/`distortion_tolerance` (`auto` = deterministic form heuristic, no model call) inherit the slot's labels unless restated

Parameters not published.

memory_forget(scope, ...)Forget from one store: `memory` (by text/substring/source/episode/tag) and `fact` hard-delete; `world` and `lesson` (by entity/attribute) retire the slot with an audit row — reversible via `memory_graph_review(action="restore_slot")`

Parameters not published.

memory_graph(entity, depth?, include_facts?, to?, relation_filter?)Entity neighborhood (≤3 hops) with derived transitive/inverse edges and per-edge `EXTRACTED/INFERRED/AMBIGUOUS` provenance tags; `to` returns the shortest path between two entities

Parameters not published.

memory_graph_relate(src, relation, dst, ...)Assert a typed edge (closed relation vocabulary; re-assertion bumps confidence)

Parameters not published.

memory_graph_review(action, proposal_id?, proposal_ids?, proposals?, scope?, src?, dst?, relation?, store?)Work the review queue: `list` / `propose` / `relate` (link a pair *and* dismiss its duplicate proposal in one call) / `dismiss_pair` / `dismiss_slot_pair` / `restore_slot` / `accept_link` / `reject_link` / `accept_merge` / `accept_junk` / `reject_entity` (merge/entity decisions are audit-stamped `decided_by=agent` over MCP, `human` via Console); `proposal_ids` settles many id-actions in one call; `restore_slot` undoes a `memory_forget(scope="lesson"/"world")` retirement — `store` + the retired `entity

Parameters not published.

memory_graph_unrelate(src, relation, dst)Retract an edge (superseded, kept for audit)

Parameters not published.

memory_history(entity, attribute?)With `attribute`: version timeline at a slot, with writer/temporal stamps. Without: the entity's causal chain — dated fact/entry/edge/lesson events ("what led to X")

Parameters not published.

memory_lesson_search(query, top_k?, verbose?)Recall learned lessons for the task at hand — heed `polarity` `-` dead-ends; `re_verify` flags lessons whose subject facts changed since

Parameters not published.

memory_message(action, to?, text?, request_id?, reply_to?, after?, message_id?)Experimental addressed mail: `send`, non-destructive `receive`, or explicit recipient `ack`; requires authenticated adapter binding, remains outside memory retrieval, and never grants user approval

Parameters not published.

memory_outcome(task, outcome, about?, detail?, polarity?, episode?, used_ids?)Record a procedural outcome signal (`success`/`failure`/`correction`); the dream distils signals into lessons. `used_ids` names the search hits the work actually turned on — each credits every `retrieval_events` row in the session window that served it with a `retrieval_uses` label (`used_via=outcome`), the relevance signal a learned reranker trains on; same session, within `use_window_seconds`, or nothing is credited

Parameters not published.

memory_recall(query, hops?, top_k?, verbose?)Multi-hop retrieval for relational questions; `low_confidence: true` → fall back to `memory_search`

Parameters not published.

memory_recent(n?, sources?, episodes?, tags?, verbose?)Newest stores, timestamp-ordered (debug + session catch-up)

Parameters not published.

memory_relation_define(name, description, ...)Grow the closed relation vocabulary (deliberate, rare act)

Parameters not published.

memory_search(query, top_k?, filters..., rerank?, bm25?, explain?, verbose?)Associative retrieval; canonical `cortex` facts surface ahead of recall hits, each dated (`asserted_at` / `last_confirmed` / human `age`, plus `stale` when it has rotted); `explain=True` attaches a ranking trace

Parameters not published.

memory_session_title(title, episode?)Name THIS session's auto-opened episode (default titles are generic); `episode` is your session handle from the briefing — concurrent sessions share one HTTP connection, so pass it to land the rename on your own episode

Parameters not published.

memory_stats()Store occupancy, hit rates, totals

Parameters not published.

memory_store(text, source?, tags?, origin?, episode?, authority?, distortion_tolerance?)Remember one durable fact / decision / observation (canonical facts reach the cortex via the dream pass or `memory_fact_set`); `authority`/`distortion_tolerance` label the speech act and how exactly it must survive — `auto` (default) is a deterministic form heuristic, no model call, and both labels are inherited through supersession unless restated

Parameters not published.

memory_supersede(old_text?, new_text, entry_id?)Correct the selected entry by ID, or one unique exact-text match; ambiguous/missing targets fail closed. Keep the old entry as history; `derived_flagged` names canonical facts built on it (flagged, never rewritten)

Parameters not published.

memory_world_search(query, top_k?, verbose?)Search world facts — each carries `effective_confidence`, a `stale` flag, and its citation

Parameters not published.

memory_world_set(entity, attribute, value, source_url?, ...)Assert a cited WORLD fact (external knowledge; age-decayed trust by freshness class)

Parameters not published.

Ask AI

✦

Ask AI about PseudoLife Memory

Powered by Claude · Grounded in docs

I know everything about PseudoLife Memory. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About PseudoLife Memory

How do I install PseudoLife Memory?

Run uvx pseudolife-mcp, then add the server to your MCP client's configuration.

Is PseudoLife Memory safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is PseudoLife Memory still maintained?

Yes — the last commit was 7 hours ago. The repository has 6 stars and 1 forks.