Skip to main content

MemNet

Mission working memory for LLMs. A named session graph (GQL node/vertex, edge/relationship, property) that agents pin and mutate — not a notepad in chat, and not the search library.

MemNet sits between LLM call pipelines and data search (MN-REQ-00). Corpus lookup stays on the host (grep, ingest, optional RAG); it may propose locators. In the session, kinds/tags are overlapping cues; recall is serial — cue, then a bounded pin_map neighbourhood. It is not GraphRAG, not a vector store, and not AgensGraph.

This repo ships the engine + generic MCP only. Product shape: docs/SHAPE.md. Pinned role: working set of a few technical documents (atoms and locators, not PDF bytes) plus live TSK/USR/MOD, re-read fast. Tens of MiB typical; hundreds of MiB still in role; gigabytes = RAG/cabinet.

Package memnet-llm (CLI memnet). Python ≥ 3.11. Hatch 0.19.11; last published PyPI wheel is memnet-llm==0.19.6 until this cut is uploaded (0.19.11 honesty c: catalog cross-session satisfy locators + CousinSysMLEdge mustNotInventUploadBind). 1.0 stays unclaimed. SemVer meaning (a.b.c): docs/ROADMAP.md.

Install + quick CLI

pip install memnet-llm
# or pin published: pip install memnet-llm==0.19.6
# optional extras (drivers only — not an AgensGraph server):
# pip install 'memnet-llm[mcp]'
# pip install 'memnet-llm[agensgraph]'
# contributors: pip install -e ".[dev,mcp]"

CLI needs a serve process. Prefer local IPC; TCP is the fallback.

# Terminal 1
export MEMNET_IPC_SOCKET=/tmp/memnet.sock
memnet serve --ipc

# Terminal 2 (same MEMNET_IPC_SOCKET)
memnet session open --map-file parts/common/memnet/memnet/examples/schema.example.txt
# demo-world map for tests; warehouse GQL below is illustrative (not that world's field list)
# stderr prints MEMNET_SESSION=mn_… — pass it as --session (serve proxies argv, not your shell env)

memnet mutate --session mn_… --stdin <<'EOF'
CREATE (t:TSK {goal:'Clear warehouse', status:'in_progress'})
CREATE (n:NPC {role:'helper', status:'active'})
MATCH (n:NPC {role:'helper'}), (t:TSK {goal:'Clear warehouse'})
CREATE (n)-[:helps {note:'labour'}]->(t)
EOF

memnet query find --session mn_… --kind TSK --limit 8
memnet query pin-map --session mn_… --kind TSK --locator 'goal=Clear warehouse' --depth 2

Shaped pin map (illustrative; nickname id only if set):

(:TSK {goal: 'Clear warehouse', status: 'in_progress'})
(:NPC {role: 'helper', status: 'active'})
(:NPC {role: 'helper'})-[:helps {note: 'labour'}]->(:TSK {goal: 'Clear warehouse'})

Create by labels+properties (CREATE () is legal). leftover id:'NEW' mint / @ID: AssignedIdMap is leftover, not product. Each turn pin_map(q) (or skip); drop prior maps from the prompt; leftover --anchor is a nickname cue. The agent dialect is GQL only (openCypher-shaped). Wire SSOT: docs/grammar/gql-wire-profile.md. Layer accept is dead.

MCP in-process (memnet-mcp) does not need serve — that's the usual single-agent path.

Session pipe

Handoff between modules/agents is the sessionId (treat it as a secret capability). The peer re-pin_maps — don't dump the graph into chat. Keep working/mission memory distinct from other product handles (e.g. a company store id); mixing those is an app concern, not MemNet's job.

Import absorb vs shared session

  • Path A — same sessionId; peers just re-pin_map. No import.
  • Path B — separate member session; lead absorbs a bounded slice via memnet import-slice (pattern match, not MERGE-by-id). leftover keep/reject/remint id_policy is leftover, not product. That's absorb into the lead SSOT, not append. ImportGuard / CheapLlmImportGuard is a user-selectable optional soft LLM (feature stays; not deprecated). Absorb works with the key unset. Set MEMNET_IMPORT_GUARD_API_KEY on serve to activate (optional MEMNET_IMPORT_GUARD_BASE_URL / MEMNET_IMPORT_GUARD_MODEL). --no-guard skips the soft pass for one call. Hard ImportAbsorb always runs. Teach: docs/LLM-GUIDE.md.

ACL + transport

CapsPolicy ACL (shipped; off by default until session acl-enable): who (caller) / pin_map vs mutate / WorkerWriteScope hard reject / optional missionId+lease bind.

RSV neighbourhood reserve exists (memnet reserve / extend / release; llm_id + TTL; pin map may show ## Reserves).

Transport: in-process MCP default (one graph per process). Shared graph: memnet serve --ipc (MEMNET_IPC_SOCKET) or TCP memnet serve (127.0.0.1:18765). Multitask / parallel workers need a shared serve — not default in-process.

Durable: optional client memnet-llm[agensgraph]; the cabinet is external and not vendored. 0.7 is adapter + operator round trip (no runtime caller) (liveCabinetClaimed); CI skips unless MEMNET_AGENSGRAPH_URL is set. Neo4j is retired (#187). MEMNET_NEO4J_* is ignored (one log warning); the engine still starts.

Deferred (honest)

  • Hosted AgensGraph as a product service (operator runs the server; this repo does not vendor it)
  • N-server session pipe (#47)
  • SysML file reverse / pin-map re-ingest (MN-REQ-11.5 SHOULD / #66) — 0.19 writes cue pin_map GQL out; identity merge on the way back is later
  • Host search / RAG as a MemNet tool — application nest only (docs/extras/memnet-host-search-nest.md)
Doc Role
docs/LLM-GUIDE.md Agent playbook (GQL only)
docs/SHAPE.md Product shape from the problem
docs/grammar/gql-wire-profile.md GQL wire SSOT
docs/ROADMAP.md Version map SSOT
sysml-models/ Requirements / verify
docs/operations/multi-agent-sessions.md Multitask ops
docs/README.md Full docs index

Layout: LAYOUT.md · AGENTS.md. Novel-writer is out: DROP-NOVEL-WRITER.md.

Licence

MIT

Release files for memnet-llm 0.19.15

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for memnet-llm 0.19.15
File Size Uploaded
memnet_llm-0.19.15.tar.gz 315.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for memnet-llm 0.19.15
File Interpreter ABI Platform
memnet_llm-0.19.15-py3-none-any.whl Python 3 none any Details

Total release size: 597.5 kB

Release files / memnet_llm-0.19.15.tar.gz

Download URL memnet_llm-0.19.15.tar.gz
Size 315.7 kB
Tags Source
SHA-256 checksum
How to use checksums
c87b3df399cdeb82d738cf769f6b109985efa7c536a87c2dc7e6522c5dd486f6
BLAKE2b-256 checksum
How to use checksums
6076f0be68ad933a888f153a8544b6c7bbda2406bf4795c8622ba7da23f34477
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5

Release files / memnet_llm-0.19.15-py3-none-any.whl

Download URL memnet_llm-0.19.15-py3-none-any.whl
Size 281.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
06809f656afc352376d3972006702346a1182a2fe436a2b66bd7f79b056033a9
BLAKE2b-256 checksum
How to use checksums
5bbb8b6ab2c50cfbe1ef25f43484630ac09f44a542e43b9ccf60ba692a7ca460
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page