MemNet
Working memory for LLMs. One session graph that agents pin and update — without dumping everything into chat.
That's the whole product idea: a shared scratch space for a mission, not a notepad in the thread. It isn't AgensGraph/Neo4j, and it isn't an app EvidenceCentre — those stay downstream. This repo ships the engine + generic MCP only.
Package memnet-llm (CLI memnet). Python ≥ 3.11.
Install + quick CLI
pip install memnet-llm
# optional: pip install 'memnet-llm[mcp]'
# optional durable client (psycopg only — not an AgensGraph server):
# pip install 'memnet-llm[agensgraph]'
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
# stderr prints MEMNET_SESSION=mn_… — pass it as --session (serve proxies argv, not your shell env)
memnet add --session mn_… --stdin <<'EOF'
CREATE (t:TSK {id:'NEW', goal:'Clear warehouse', status:'in_progress'})
CREATE (n:NPC {id:'NEW', role:'helper', status:'active'})
EOF
# stderr @ID lines mint real ids (e.g. TSK1, NPC1) — copy them
memnet add --session mn_… --stdin <<'EOF'
MATCH (n:NPC {id:'NPC1'}), (t:TSK {id:'TSK1'})
CREATE (n)-[:helps {id:'NEW', note:'labour'}]->(t)
EOF
memnet query pin-map --session mn_… --anchor TSK1 --depth 2
Shaped pin map (illustrative):
(:TSK {id: 'TSK1', goal: 'Clear warehouse', status: 'in_progress'})
(:NPC {id: 'NPC1', role: 'helper', status: 'active'})
(:NPC {id: 'NPC1'})-[:helps {id: 'E1', note: 'labour'}]->(:TSK {id: 'TSK1'})
Create with id:'NEW'; patch/settle with known ids only. The agent dialect is GQL only (openCypher-shaped): shaped pin_map read + gated mutate. 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(keep/reject/remint). That's absorb into the lead SSOT, not append. Optional ImportGuard soft policy: host hook and/or env-gated CheapLlmImportGuard (MEMNET_IMPORT_GUARD_API_KEY; optionalMEMNET_IMPORT_GUARD_BASE_URL/MEMNET_IMPORT_GUARD_MODEL).--no-guardskips even when the key is set.
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]; cabinet is external and not vendored. Live cabinet is not claimed.
Deferred (honest)
- Live AgensGraph cabinet (client hydrate/flush exists; live path not claimed)
- N-server session pipe (#47)
- Pin-map export / round-trip (MN-REQ-11.1–11.5 / #66) — Path-B ingest domains are shipped (#64); export is separate
Links
| Doc | Role |
|---|---|
docs/LLM-GUIDE.md |
Agent playbook |
docs/grammar/gql-wire-profile.md |
GQL wire SSOT |
docs/ROADMAP-0.5.md |
0.5 plan |
sysml-models/ |
Requirements / verify |
docs/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
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file memnet_llm-0.4.6.tar.gz.
File metadata
- Download URL: memnet_llm-0.4.6.tar.gz
- Upload date:
- Size: 242.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb860ab720448095451b377d4ec65ad2ee0011516c468f60d02f377a73e1b97d
|
|
| MD5 |
4ce80722c2292884aa8b0b891b1f8e0a
|
|
| BLAKE2b-256 |
d6102b3770342ec97df4434b427491d24dcf63355c9aed40026e8c3c59362785
|
File details
Details for the file memnet_llm-0.4.6-py3-none-any.whl.
File metadata
- Download URL: memnet_llm-0.4.6-py3-none-any.whl
- Upload date:
- Size: 238.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3c31f4bb67d86a6c3c08d2cacfb4232c38297f5c975091b8b01aff1be22cc942
|
|
| MD5 |
9dde72e6b2558cc08e78fd6d7c60932c
|
|
| BLAKE2b-256 |
4a179fc23779e79495e06c361b80906d6bc13c9cccd2da76df5ac5a1e1e78204
|