# InfiniteMem – deterministic episodic memory, LoCoMo 70.49

> Source: <https://github.com/marcot3ssar1/InfiniteMemOs>
> Published: 2026-09-03 20:47:42+00:00

Deterministic, self-hosted episodic memory for agents (K3 engine):
**1M episodes / 145M tokens per deployment** — ~1,450 novels, ~1,130× a
GPT-4o context window, ~27 years of chat. Details: [CAPACITY.md](/marcot3ssar1/InfiniteMemOs/blob/main/CAPACITY.md).

LoCoMo QA 70.49% under equal protocol, reproducible evaluation glue.
**No implementation sources are included by design. Closed source — see NOTICE.**

**Try it:** an MCP server with a free trial is coming — run infiniteMem
from Claude Desktop and your agents without sharing data externally.
Contact via repository for trial access.

`paper/`

— scientific report v2 (LoCoMo + LongMemEval, stronger-reader rows, world-model gate, reranker study, limits, references).`harness/`

— evaluation scripts only (dataset fetch checks, fresh embedding via NVIDIA API, numpy retrieval crosscheck, QA answer+judge via OpenRouter, rerank gate). They drive the closed engine as a black box and reveal nothing about its internals.`results/`

— certified numbers:`leaderboard.json`

(LoCoMo, SOTA2-ready),`leaderboard_lmem.json`

(LongMemEval-S),`readers.json`

(stronger-reader rows + world-model gate), per-question`qa_cache.jsonl`

(3070 records, no gold texts), retrieval and QA reports, reranker negative-result report.

- Fetch
`snap-research/locomo`

`data/locomo10.json`

(CC BY-NC 4.0, non-commercial, cite Maharana et al., ACL 2024) and verify`SHA256 79FA87E9…`

. - Set env keys (never commit):
`NVIDIA_API_KEY`

(embeddings`llama-nemotron-embed-vl-1b-v2`

, 768-D, passage`Speaker: text`

/ query raw) and`OPENROUTER_API_KEY`

(answer+judge`openai/gpt-4o-mini-2024-07-18`

, temp 0, verbatim Mem0 prompts). - Run harness in order:
`exnovo_embed.py`

→`eval_fresh_retrieval.py`

→`exnovo_qa.py --mode k3`

+`--mode oracle`

. Expected: retrieval`78.85/74.10`

, QA`k3 70.49 / oracle 84.89`

(±0.5pp API variance).

Black-box engine, brute top-10 single-shot, dedup off, no rerank, 1 run. Answer/judge models and prompts pinned (see paper §3, §6). Dataset CC BY-NC 4.0. Contact via repository for engine access.