NevaMind AI
companyScores
1 product on the map — 1 open-ish.
Openness
3 medium confidence- license
- memU-Modified-Apache-2.0 (LICENSE.txt is the Apache License 2.0 text with the section 2 copyright grant rewritten in MIT wording and an added notice-retention condition, and other clauses reworded)
- source
- public
- core features withheld
- no — the 340-path tree at 12d144c holds the memory service, storage backends, embedding providers and every host adapter with no ee/, enterprise/, commercial/ or proprietary/ path, and memU Cloud is a free hosted backend for the same three operations
- commercial
- memU Cloud hosted backend at memu.so
memU's whole memory pipeline, from the session-log adapters to the storage and retrieval service, is in the public repository and runs locally with the user's own storage and embedding provider. Its LICENSE file is the Apache 2.0 text with the copyright grant rewritten in MIT-style wording, so it is not the approved Apache license the project names elsewhere, though nothing in it limits who may use the software or at what scale.
- https://memu.pro recorded 2026-11-20
The product site offers memU Cloud as "100% free" and an enterprise option of "managed cloud or a supported self-hosted pilot".
- https://memu.pro/faq recorded 2026-11-20
The FAQ says "memU is available on GitHub under the Apache-2.0 license. The repository contains the Python package, CLI, installation skill, and host adapters", and that self-hosting needs only an embedding provider and local storage.
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/docs/adr/0012-cloud-backed-agentic-backend.md recorded 2026-11-20
The cloud-backend design record says the hosted memU service exposes the same three operations as the local MemoryService, selected by MEMU_MEMORY_MODE, with local remaining the default.
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/LICENSE.txt recorded 2026-11-20
LICENSE.txt is headed "Apache License Version 2.0" but its section 2 grants a "license to use, reproduce, modify, merge, publish, distribute, sublicense, and/or sell copies of the Work" subject to keeping the copyright and permission notice, with other clauses reworded; it ends "Copyright 2024 MemU Team".
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/pyproject.toml recorded 2026-11-20
The package manifest builds memu-cli from src/memu; its license line, license = {file = "LICENSE"}, is commented out.
- https://www.apache.org/licenses/LICENSE-2.0.txt recorded 2026-11-20
The canonical Apache License 2.0 section 2 grants a "copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work".
Adoption
1 medium confidenceAdoption is read from monthly downloads of memu-cli on PyPI and its npm launcher, the package every memU host adapter installs whether it stores memory locally or in memU Cloud. The memu-py package from the project's earlier framework line is left out, and installs say nothing about how many agents keep using it.
- https://api.npmjs.org/downloads/point/last-month/memu-cli recorded 2026-11-20
20 downloads of memu-cli on npm between 2026-10-20 and 2026-11-18.
- https://pypi.org/pypi/memu-cli/json recorded 2026-11-20
PyPI lists memu-cli, "Personal memory as files", with homepage and bug tracker at github.com/NevaMind-AI/MemU.
- https://pypistats.org/api/packages/memu-cli/recent recorded 2026-11-20
455 downloads of memu-cli on PyPI in the trailing 30 days.
- https://registry.npmjs.org/memu-cli/latest recorded 2026-11-20
The npm memu-cli is a "Thin launcher for the PyPI package memu-cli", published from the npm/ directory of NevaMind-AI/MemU.
Capability
2 medium confidencememU retrieves across three separate stores of memory, workspace and skill files, and it supplies the instructions for distilling session logs into them. The distilling and merging are done by the host agent's model, not by memU, whose memory service makes no model calls of its own, so memU organizes and serves memory rather than deciding what to keep.
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/docs/adr/0007-three-independent-memory-lines-wiki-graph.md recorded 2026-11-20
The design record splits memory into three lines, chat to MEMORY.md, workspace files to INDEX.md and execution traces to SKILL.md, each with its own store and hybrid embedding and BM25 retrieval.
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/README.md recorded 2026-11-20
The README says a scheduled bridging task "slices new session logs into self-contained job files; the agent itself distills them into memory/skill Markdown", which memU commits, indexes and retrieves before answering, and that "MemoryService makes no LLM or chat calls".
- https://raw.githubusercontent.com/NevaMind-AI/memU/main/src/memu/hosts/bridging/instructions.py recorded 2026-11-20
The job templates tell the agent to read existing memory or skill files, then do nothing, patch an existing file with the merged content, or create a new one.