Website · Quickstart · Documentation · Examples · Migration · Measured results · Trust evidence · Releases · npm · Contributing · Issues

[!NOTE]

Which Mnemosyne is this? This repository is the TypeScript package published on npm as mnemosy-ai, with its site at mnemosy.ai. It is a separate project from mnemosyne-oss/mnemosyne, the Python memory library published on PyPI as mnemosyne-memory; the two share a name, not code or maintainers. Please file issues for that project in its own repository.

Try it in 30 seconds

The 3.0.0-rc.2 demo runs offline on synthetic corpora, with no API key and no model, and measures each claim while it runs:

npx -y -p mnemosy-ai@next mnemosy demo

The last line of each of its five moments, from one run (timings vary by machine; the pass bars printed after each line are omitted here):

PROOF  replay determinism: 1000/1000 identical, 24000/24000 as-of answers = ground truth   [PASS]
PROOF  downstream repair: undeclared invalidated 3/3, accepted edges true 3/3, stale after correction 0 (11 probes)   [PASS]
PROOF  blame precision / time-to-locate: precision 1.00, 0.38 s, 2000 records   [PASS]
PROOF  poisoning suite v1, live: 227 cases, 0 escapes, 0 false quarantines   [PASS]
PROOF  consolidation receipts: kept 1 (delta +2), rolled back 2 (regression, invariant violated), rollback identical hash true, chain verified 4 receipts   [PASS]
5/5 moments proved.

What each moment proves, and what it does not. Then give the memory to Claude Code (other clients: Install and connect an agent):

claude mcp add mnemosyne -- npx -y -p mnemosy-ai@next mnemosy mcp --db ./.mnemosyne/memory.sqlite --workspace my-project --agent assistant

For the stable release, write [email protected] in place of mnemosy-ai@next; on 2.0.0, mnemosy demo runs the earlier single-scenario demo.

Contents: 3.0: the breakthrough release · Install and connect an agent · Measured results · Choose your engine · A working demonstration · Corrections in code · Tune the dense index · What you can build · Entry points · Migrate · Limits · Operational boundaries · Build with us

New in 3.0.0-rc.2: the breakthrough release (pre-release on npm next)

3.0 is the breakthrough release: past beliefs replay exactly, corrections retire what depended on them (including dependencies nobody declared, once accepted), bisect names the record behind a wrong answer, a poisoning gate is checked against a reproducible attack suite, and consolidation is reversible with signed receipts. Each of these is documented and tested below. 3.0.0-rc.2 is a release candidate on the npm next channel: npm install mnemosy-ai@next installs it, while npm install mnemosy-ai still installs the stable 2.0.0. Every number below was measured offline, with no API key, no paid model and no LLM judge. Each one reproduces with the commands in Benchmarks and trust evidence, which also lists what is not claimed.

| Measurement | Result | Protocol | |---|---|---| | PrecisionMemBench | 70/77 single-turn, 11/12 session turns (rc.1: 22/77 unfiltered, 48/77 with tuned wrapper filters, session 6/12) | Public 35-belief fixture the controls were designed against, protocol-exact, retrieval mode, no wrapper-side filter, no LLM judge · protocol | | Poisoning suite v1, consolidation on | 0/167 escapes, 0/60 false quarantines (85/167 escape without the gate) | 227 synthetic cases, lexical path, 294 gate decisions · protocol | | Dependency suite v1 | recall 96.05 %, precision 98.06 %, 0 stale procedures with the premise guard (inference alone: 7/248 stale; guard false-hold rate 92.78 %) | Synthetic corpus, seed 20261028, 120 corrections, accept-all eval reviewer · protocol | | Replay determinism | 1000/1000 identical states, 24,000/24,000 as-of answers | Two readers of one store at 1000 seeded cut points; answers against ground truth from the plan · protocol | | Bisect | precision 1.00 in 1.53 s on 2,000 records (re-runs 0.6–1.2 s; bar 60 s) | One seeded false record in a synthetic store, confirmed by re-running recall without it · protocol |

The default retrieval path did not move: LoCoMo and LongMemEval-S recall are identical before and after (regression check). Recall latency was measured only on a loaded machine; the known limits, including a slowdown of the non-default overlap scorer, are in the changelog.

• Precision you can switch on. The new opt-in controls are a names gate and guarded single-edit fuzzy matching. Empty answers are native abstentions, and the ledger records why. With the controls on, the kernel scores 70/77 single-turn cases and 11/12 session turns on PrecisionMemBench (session was 6/12 with the rc.1 filtered configuration). That run was protocol-exact, in retrieval mode, with no LLM judge, no wrapper-side filter and no wrapper kinds predicate, and the lexical and hybrid paths score the same. The 12th session turn needs an open-question kind policy that the kernel is not told about.

• Consolidation that has to earn its keep. A consolidation pass is a signed diff, replayed against the agent's own recorded outcomes. It is kept only when nothing regresses and no invariant breaks, and one command undoes it, back to the identical state hash. With consolidation on, the poisoning suite v1 run (227 synthetic cases, reproducible) has zero escapes: 0 of 167 attacks escaped and 0 of 60 benign controls were falsely quarantined, across 294 gate decisions. An ungated control lets 85 of the 167 attacks through. Consolidation gate · Signing and receipts
• Corrections that reach what nobody linked. Dependencies are inferred from successful co-use and proposed for review. Once accepted, they are declared through correct(), and runtime skills can be linked to their premises. The measurement is on a synthetic seeded corpus (dependency suite v1, seed 20261028, 120 corrections):

Inferred dependencies

• A demo that measures itself. mnemosy demo walks through five moments on synthetic corpora, offline, on the zero-model lexical path:

Each moment prints a PROOF line measured in that run. What each moment proves

npx -y -p mnemosy-ai@next mnemosy demo             # five moments, offline, each PROOF line measured live
npx -y -p mnemosy-ai@next mnemosy demo --classic   # the previous single-scenario demo

From a source checkout, run npm run build and then node dist/cli/index.js demo.

3.0 is a breaking release: the legacy vector engine moves to mnemosy-ai-legacy, which is not on npm yet; build it from a checkout or stay on mnemosy-ai@2 (3.0 migration). The release notes are in the changelog.

Install and connect an agent

npm install mnemosy-ai                   # stable: latest = 2.0.0; pin [email protected] to reproduce
npm install mnemosy-ai@next              # pre-release: next = 3.0.0-rc.2; pin [email protected] to reproduce
npx --no-install mnemosy demo            # offline: no API key, no server, no Docker

Give the memory to an MCP client. Claude Code reads .mcp.json in the project root and Cursor reads .cursor/mcp.json; both take the same server entry. The entries below run the 3.0.0-rc.2 pre-release through mnemosy-ai@next; for the stable release write [email protected] in its place, and to pin the pre-release write [email protected]. Both versions expose the same MCP tools. The database file (mode 0600) and its parent directory (mode 0700) are created on first use. Relative paths resolve from the directory the client starts the server in; use absolute paths if your client launches servers elsewhere.

{
  "mcpServers": {
    "mnemosyne": {
      "command": "npx",
      "args": [
        "-y", "-p", "mnemosy-ai@next", "mnemosy", "mcp",
        "--db", "./.mnemosyne/memory.sqlite",
        "--workspace", "my-project", "--agent", "assistant"
      ]
    }
  }
}

Claude Code can register the same server from the shell:

claude mcp add mnemosyne -- npx -y -p mnemosy-ai@next mnemosy mcp --db ./.mnemosyne/memory.sqlite --workspace my-project --agent assistant

Codex keeps MCP servers in ~/.codex/config.toml. Register the server with an absolute database path:

codex mcp add mnemosyne -- npx -y -p mnemosy-ai@next mnemosy mcp --db /absolute/path/project/.mnemosyne/memory.sqlite --workspace my-project --agent assistant

The command writes this table, which you can also add by hand:

[mcp_servers.mnemosyne]
command = "npx"
args = ["-y", "-p", "mnemosy-ai@next", "mnemosy", "mcp", "--db", "/absolute/path/project/.mnemosyne/memory.sqlite", "--workspace", "my-project", "--agent", "assistant"]

The first npx launch downloads the package; if a client gives up during that first start, install the package in the project first.

The server exposes 16 memory_* tools (memory_store, memory_recall, memory_context, memory_correct, memory_checkpoint, memory_resume, memory_observe, memory_skill, …); memory_forget is added only when the server is launched with --allow-destructive. Add --read-only to omit every mutation tool. A model cannot switch workspace, raise its own trust or report its own skill trials through MCP. Agent-readable summaries of this repository are in llms.txt and AGENTS.md; the full MCP contract is in Connect through MCP.

Measured: 409 of 500 on LongMemEval-S, with the misses printed

| What | Result | How it was measured | |---|---|---| | Answer accuracy, LongMemEval-S, all 500 questions | 409 / 500 correct (81.8%), Wilson 95% CI 78.2–84.9; exact match 7.6% | Mnemosyne reranked retrieval, top-20 hits packed to 16 KB, read by claude-sonnet-4.6, judged by claude-haiku-4.5. Prompt and budget were chosen on 100 of the questions; the other 400 score 82.3%. | | Reranker gain, LoCoMo, 1,531 annotated questions | MRR@10 0.461 → 0.624, +0.163 (paired bootstrap 95% CI 0.146–0.181; 599 wins, 133 losses) | The same hybrid candidate set with and without the bundled cross-encoder, on the shipped build. | | Against Mem0 OSS, same corpus, chunks, K, packing budget, scorer, one process | LoCoMo recall@10 73.57 vs 63.72 with reranking; our unreranked path loses to Mem0 at every K; on LongMemEval-S the two tie on recall@20 and Mem0 takes MRR | COMPARISON.md, every loss in the same tables |

What these numbers do not say. The 81.8% is not a paired gain over the earlier 71.2%: that baseline used a different 250-question sample, prompt and budget, so the improvement belongs to the whole bundle of changes. The reader is nondeterministic; rerunning one configuration moved its score by about a point. Retrieval numbers measure coverage, not answers. Two Tier 1 targets of 2.0.0 are not met and ship disclosed: recall latency at one million records is p95 139–223 ms against a 50 ms goal (opt-in indexMode: 'hnsw', see Tune the dense index), and contextual reranking ships at 71.98% all-evidence hit against a 72.80% gate, 0.82 points (13 of 1,531 questions) short; the best variant tried was still four short and was not merged. Commands and raw outputs are in reports/t1-targets/evidence/; the answer-accuracy and gate results are restated with their commits in the changelog, and the Mem0 and reranker retrieval tables are in COMPARISON.md.

Choose your engine

Both engines ship in 2.0.0; from 3.0.0-rc.2, mnemosy-ai ships the Local Engine and the Vector Engine moves to mnemosy-ai-legacy. Choose the storage and runtime that fit your application:

| Engine | Best starting point | SDK entry point | Guide | |---|---|---|---| | Vector Engine | An application using the existing service-backed memory architecture. Requires configured external services. | createMnemosyne from mnemosy-ai 2.x; from 3.0 in the separate mnemosy-ai-legacy package | Working example · Version 2 changes · 3.0 split | | Local Engine | A self-contained SQLite memory store with evidence, corrections and agent lifecycle tools. | createLocalMemory from mnemosy-ai/local | Local API · Agent lifecycle |

The MemoryAgent adapter uses the Local Engine's runtime. These engines have separate schemas and do not automatically migrate or synchronize data. To transition gradually, explicitly connect your existing store through the read-only migration bridge; it leaves that store unchanged.

Engine choice is separate from version: mnemosy-ai@latest is 2.0.0 and contains both engines; the 1.x line stays installable as mnemosy-ai@1. Upgrading from 1.x is a breaking change: read the migration notes before upgrading an existing Vector Engine application. From 3.0.0-rc.2 (npm next), the Vector Engine has moved out of mnemosy-ai into the mnemosy-ai-legacy package, which is not on npm yet; see the 3.0 migration notes.

Start with a working demonstration

Install the package in your project. Node 24 is recommended; the local memory engine needs no model API key, database server, or Docker.

npm install mnemosy-ai                   # stable 2.0.0; or mnemosy-ai@next for the 3.0.0-rc.2 pre-release
npx --no-install mnemosy demo
npx --no-install mnemosy learning-demo

Unqualified npm install mnemosy-ai follows the latest channel, which is 2.0.0 from 27 October 2026; pin [email protected] for reproducible deployments. npm install mnemosy-ai@next installs the 3.0.0-rc.2 pre-release; pin [email protected] to reproduce it. If you are upgrading from the 1.x line, read the migration notes first: version 2 changes vector retrieval scoring, startup indexing and erasure, and does not migrate an existing database. Evaluate on your own workload before production. Python registry publication is separate; the bundled Python client can be installed from the checkout.

To build and run the same release from source (use --branch v3.0.0-rc.2 for the pre-release):

git clone --branch v2.0.0 --depth 1 https://github.com/28naem-del/mnemosyne.git
cd mnemosyne
npm ci --ignore-scripts
npm run build
npm run demo
npm run demo:learning

In 2.0.0, the first demo uses a temporary database to show a handoff, correction, private scope and forgetting. From 3.0.0-rc.2, mnemosy demo is the five-moment demo and the 2.0.0 demo is mnemosy demo --classic. The learning demo exercises capture, a scripted observation job, skill trials, explicit sharing and correction-driven retirement. Both run real local APIs with deterministic fixtures and no model calls. Choose your next example.

For full contributor validation, run npm run check, npm run check:docs and npm run check:public. 2.0.0 is the 2.0.0-rc.10 candidate promoted to stable with no source change (one dependency security patch, zod 4.6.2 → 4.6.7, is noted in the changelog); it carries the Tier 1 retrieval work (hybrid default, cross-encoder reranking, opt-in dense index and temporal routing) over the RC9 packaging. The recorded evaluation reports remain historical measurements of the versions and conditions they name.

To consume your built checkout from another project, run npm install /absolute/path/to/mnemosyne in that project. Keep the checkout and its dist directory available. The older RC8 GitHub release and checksummed downloads remain unchanged.

A correction should change what the next agent does

import { createLocalMemory } from 'mnemosy-ai/local';
const memory = createLocalMemory({
  path: './agent-memory.sqlite',
  workspaceId: 'catalogue',
  agentId: 'designer',
});
const brief = memory.store({
  text: 'Product images must be 1200 by 900 pixels.',
  kind: 'fact',
  key: 'catalogue.image-size',
  source: { uri: 'brief://catalogue/v1' },
  trust: 'observed',
  visibility: 'workspace',
});
const procedure = memory.store({
  text: 'Export catalogue product images at 1200 by 900 pixels.',
  kind: 'procedure',
  source: { uri: 'run://designer/export' },
  trust: 'observed',
  dependencies: [brief.id],
  visibility: 'workspace',
});
memory.correct(brief.id, {
  text: 'Product images must be 1600 by 1200 pixels.',
  source: { uri: 'brief://catalogue/v2' },
  reason: 'The delivery specification changed.',
});
console.log(memory.get(procedure.id)?.status); // invalidated
const context = memory.compile({
  query: 'catalogue product images',
  maxTokens: 2048,
});
console.log(context.text); // Send eligible context to your responder.
// Inspect context.citations and context.uncertainty alongside the text.
memory.close();

The old procedure remains inspectable but is no longer eligible as current guidance. Dependencies are declared by the controller. In 3.0, the dependencies module can also propose undeclared dependencies from successful co-use, and a reviewer accepts or rejects each one. observed means the host recorded the source; it does not certify its truth. The default context counter measures UTF-8 bytes conservatively, not a model's tokenizer. Context contract.

Tune the dense index

Recall works without any of this. These three options exist for stores large enough that the defaults stop being the right trade, and all three are opt-in.

const memory = createLocalMemory({
  path: './agent-memory.sqlite',
  workspaceId: 'catalogue',
  agentId: 'designer',
indexMode: 'hnsw',            // 'exact' | 'auto' (default) | 'sqlite-vec' | 'hnsw'
  sqliteVecPath: '/opt/lib/vec0.dylib',  // explicit extension path; no env-var equivalent
  cacheSize: -65536,            // PRAGMA cache_size: negative = KiB, positive = pages
});

indexMode — which dense index to search. Defaults to $MNEMOSYNE_INDEX_MODE, else auto.

| mode | what it does | |------|--------------| | exact | Scores every authorized vector. No optional binaries, no index files, and the answer every other mode is measured against. | | auto (default) | sqlite-vec when the extension loads, otherwise exact. Still an exact search — vec0 scores the same vectors in C instead of in JS. | | sqlite-vec | As auto, but throws instead of degrading silently when the extension is unavailable. | | hnsw | Approximate and sublinear, for stores past a few hundred thousand vectors. The one retrieval component here that can miss a true neighbour — which is why it is never selected on your behalf. Its 50 ms p95 target at 1M records is not met: 139–223 ms measured (see CHANGELOG). |

Asking explicitly for sqlite-vec or hnsw and not getting it is an error, not a downgrade: those two modes throw when the backend is unavailable. auto is the only mode that degrades, and it only ever degrades to an exact search, never to an approximate one.

No mode changes what a record scores or whether it may be returned. Every candidate an index proposes is re-authorized and rescored against the stored vector before it reaches you, so the index is a shortlist, never an authority.

sqliteVecPath — an explicit filesystem path to a sqlite-vec loadable extension, overriding the bundled package's own resolution. Only consulted when indexMode is auto or sqlite-vec.

There is deliberately no environment-variable equivalent. An env-controlled path would make every LocalMemory opened on the machine dlopen whatever that variable pointed at, by default and without the caller asking. Loading a native extension is a decision the calling code has to make in the open, so it lives in the constructor and nowhere else.

cacheSize — PRAGMA cache_size, applied on every open, in SQLite's own units: a positive value is a page count, a negative value is a KiB budget. Defaults to -65536 (64 MiB), and a negative value is the recommended form since page size can vary. Must be a nonzero integer of magnitude at most 2,097,152.

A larger page cache buys fewer trips through the OS page cache for the shortlist rescore and the BM25 postings that the hot recall path reads on every query. It matters once the working set stops fitting in the few megabytes SQLite would otherwise settle for on its own — and it is a real memory cost, charged per open connection, so it is set rather than guessed.

What you can build

| Capability | Behavior | Developer guide | |---|---|---| | Memory with evidence | Private-by-default records, explicit sharing, corrections, conflicts, source history and dependent retirement. | Local API | | Continuity across agents | Structured checkpoints preserve goals, decisions, artifacts and next actions; source changes can retire obsolete handoffs. | Agent lifecycle | | Adaptive context | Budgeted observations, hierarchical summaries and expandable original source bytes, with evidence revalidation. | Context | | Recall across words and meaning | Scoped BM25 by default; optional embeddings, hybrid fusion and reranking over authorized records. | Local semantic retrieval | | Memory across time | Separate asOf and knownAt queries, scheduled corrections and causal invalidation history. | Runtime | | Evidence-gated skills | Candidate procedures, explicit trial requirements and retirement after failed or changed evidence. | Skills and trials | | Source-backed profiles | Typed fields report supported values, unknowns or conflicts and revalidate their inputs. | Profiles | | Silent-staleness checks | Explicit source policies, last-confirmed evidence, bounded probes and action-bound dependency checks. | Freshness | | A controlled transition | Read-only access to your previous store, gradual local preference, reconciliation and routing rollback. | Gradual migration | | Full import and recovery | Eleven export profiles, preview, atomic application, replay protection, guarded undo and whole-database backups. | Import · Recovery | | Host-controlled processing | Durable bounded jobs, source-backed project models, outcome traces, entity relations and staged changes. | Runtime |

Local Engine, several entry points

flowchart LR
  Host[Your agent or application] --> Interfaces[TypeScript · MCP · CLI · HTTP / Python]
  Interfaces --> Runtime[Capture · Context · Trials · Action checks]
  Runtime --> Store[(Local SQLite memory)]
  Store --- Evidence[Sources · History · Dependencies · Outcomes]
  Runtime -. explicit configuration .-> Models[Optional model providers]
  Runtime -. read-only adapter .-> Previous[Previous memory system]

The host chooses identities, trust assertions, providers and execution budgets. Construction starts no worker or model download. MemoryAgent can prepare context before a turn and capture supplied visible input/output afterward; background work runs only when the host starts it. Host loop.

The local database holds memories, vectors and runtime state. Optional local CPU providers run cached inference in separate processes after explicit provisioning. Their dependency requirements, model identities and licenses are documented in the local model guide. The existing backend integration remains available through createMnemosyne (in mnemosy-ai-legacy from 3.0); it does not automatically synchronize with the local engine. Version 1 migration notes.

Connect through MCP

With the npm package, use the npx entry shown in Install and connect an agent. From a source checkout, point the client at the built CLI instead; the database's parent directory is created on first use.

{
  "command": "node",
  "args": [
    "/absolute/path/mnemosyne/dist/cli/index.js", "mcp",
    "--db", "/absolute/path/data/memory.sqlite",
    "--workspace", "my-project", "--agent", "assistant"
  ]
}

Use --read-only to omit mutation tools. Forgetting requires an explicit --allow-destructive launch. Models cannot choose another workspace, promote their own trust, or report successful trials through MCP. For an authenticated service, Python access and a live inspector, see HTTP and Python. Native provider tool protocols are documented in the adapter guide.

Require stronger skill evidence

import { createLocalMemory } from 'mnemosy-ai/local';
import {
  MemoryRuntime,
  RECOMMENDED_SKILL_PROMOTION_POLICY,
} from 'mnemosy-ai/runtime';
const memory = createLocalMemory({
  path: './skills-memory.sqlite', workspaceId: 'my-project', agentId: 'assistant',
});
const runtime = new MemoryRuntime(memory, {
  skillPromotionPolicy: RECOMMENDED_SKILL_PROMOTION_POLICY,
});
// Use runtime to create candidates and record controller trials.
memory.close(); // Close after your host finishes using the runtime.

The recommended policy requires successful trials across two distinct tasks and two verifier identities. Candidates stay outside advisory context until their stored requirements are satisfied; a weaker configuration cannot lower an existing candidate's requirements. The compatibility default remains one task and one verifier. Identities and trial outcomes are controller assertions, so your host must provide real tests and independent evidence. Trial contract.

Migrate while your agent keeps working

The optional mnemosy-ai/bridge wraps your explicitly supplied legacy search adapter. It copies used records with stable origins, compares paired retrieval results, and moves from shadow to assist to preferred routing as observed coverage meets configured thresholds. Missing legacy matches remain available, and routing can return to the previous system.

The bridge keeps querying the original store for reconciliation and never writes or deletes there. Progress measures observed queries, not complete-store migration or answer quality. Host credentials, source selection and eventual cutover stay under your control. Bridge contract.

For a full export migration, choose one of the eleven supported profiles, preview the exact source bytes, then apply the reviewed plan atomically. Imports are private and untrusted by default; retry recognition, source inspection, guarded undo and erasure replay protection are included. Foreign embeddings and unsupported policy semantics are not silently converted. Full migration.

node --experimental-strip-types examples/gradual-migration.ts
node --experimental-strip-types examples/migration.ts
node --experimental-strip-types examples/maintenance.ts

These examples use isolated synthetic data. They do not connect to your existing accounts or memory stores.

Measured, with the limits visible

The paired LongMemEval S retrieval run includes all 500 questions, with positive evidence metrics on 470 annotated answerable questions. Both retrieval conditions use 20 chunks and the same 8,192-byte context budget.

| Complete annotated-session coverage | Earlier overlap scorer | Current BM25 default | |---|---:|---:| | Before context packing | 386 / 470 (82.13%) | 425 / 470 (90.43%) | | After context packing | 367 / 470 (78.09%) | 382 / 470 (81.28%) |

The 30 abstention questions remain in attempt counts without a positive retrieval score. All 500 full-history controls exceeded the context budget and are reported as overflows. The run uses same-day timestamp compatibility, including 1,475 sessions later than the stated question instant. A session hit can come from any of its chunks; it does not prove that the answer-bearing sentence reached the model. No embedding, generation or judge calls were made.

These results measure retrieval coverage against the earlier local scorer. They do not establish generated-answer accuracy or superiority over other systems. Raw reports and fingerprints · Reproduction protocol.

Against another memory system

A matched competitor benchmark against Mem0 OSS is published in COMPARISON.md — same corpus, same chunks, same K, same packing budget, all scored inside one process, with the results where Mem0 beats us printed in the same tables as the results where it does not. In short: our reranked path takes the LoCoMo headline at 73.57 recall@10 against Mem0's 63.72, our unreranked hybrid loses to Mem0 at every K on both recall and MRR, and on LongMemEval-S the two tie on recall@20 while Mem0 takes MRR. Zep and Graphiti carry a reason rather than a number: neither could be run without paid credentials. These are retrieval-coverage numbers with no reader and no judge, not answer accuracy.

A separate evidence lifecycle diagnostic tests correction, time, conflicts, failure, erasure and scope behavior. It deliberately retains a failing case: changing an unrelated field can retire a still-valid dependent rule. The engineering review and release status track this and other remaining work.

Operational boundaries

Workspace and agent IDs are trusted controller selectors, not tenant authentication. The HTTP service supplies scope-bound bearer authentication; remote TLS and enterprise identity require application deployment work. Databases and backups are plaintext. Forgetting removes covered live content and blocks known source replays, but cannot erase an older backup or a prompt already sent to a model.

Local semantic search scans the eligible indexed corpus with bounded retained candidates and a deadline. That exact scan is the default; an approximate index is available but opt-in and never selected on your behalf (see Tune the dense index), and every candidate any index proposes is re-authorized and rescored against the stored vector before it is returned. Generated observations and trial results remain fallible assertions. Action checks validate declared local dependencies before dispatch, not external transactions. Managed synchronization, model training and six validated native framework integrations are not included. Security · Deployment · Backup and restore.

Build with us

Mnemosyne is built by Aristotle Intelligence Inc., a Delaware company, and has been fully self-funded to date. For advanced memory requirements, integration discussions or investor enquiries, contact [email protected].

Use GitHub issues for reproducible bugs and feature proposals. Report vulnerabilities privately through SECURITY.md. Contributions that improve evidence retention, integration reliability or reproducible evaluation are especially useful.

Contributing · Architecture · Changelog · Code of conduct · MIT license · Third-party notices