Skip to main content

Nuramem CLI — cross-model memory from the terminal. Capture (nura save/this → server-side §15 extraction) and recall (nura search/briefing/schema) from the shell, CI, or any tool loop, with --json. Wire Nuramem's MCP server into your AI clients (nura connect) and install the memory skill (nura skill install).

Project description

Nuramem CLI (nura)

Cross-model memory from the terminal. The same memory every connected AI reads — save, recall, and connect your assistants, without leaving the shell.

Install

curl -fsSL https://get.nuramem.ai | sh    # the universal installer
# or, with a Python toolchain:
uv tool install nuramem                   #  ·  pipx install nuramem  ·  uvx nuramem

Use

nura login                      # sign in via the browser (loopback + PKCE)
nura this "we picked Postgres over Drive for the data plane"   # capture
nura search "data plane"        # recall;  nura briefing  ·  nura schema
nura --json search "stripe"     # machine-readable, for CI / tool loops

nura connect                    # wire Nuramem's MCP server into your AI clients
nura skill install              # teach a coding assistant the memory gesture
  • Capture (save/this) runs Nuramem's server-side §15 extraction.
  • Recall (search/briefing/schema) is always free.
  • nura connect safely merges a nuramem MCP entry into Claude Desktop, Cursor, Windsurf, Gemini CLI and VS Code configs (idempotent; --dry-run).
  • nura skill install drops the bundled Nuramem skill into Claude Code / Cursor / Codex / Windsurf.

Auth precedence: --api-url/explicit token → NURAMEM_TOKENNURAMEM_DEV_AUTH_TOKEN → the credential stored by nura login. CI/headless: set NURAMEM_TOKEN.

Docs and connection guides: https://nuramem.ai.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nuramem-0.1.0.tar.gz (18.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nuramem-0.1.0-py3-none-any.whl (17.6 kB view details)

Uploaded Python 3

File details

Details for the file nuramem-0.1.0.tar.gz.

File metadata

  • Download URL: nuramem-0.1.0.tar.gz
  • Upload date:
  • Size: 18.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nuramem-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0067c353d31b17e1aafc0961ceca49d680ab61a484145864cb32043c628ee357
MD5 0184043ffd8186cabb9507467caf0046
BLAKE2b-256 ba061acc5bb3df0db791026a369819d49baaf4e21b64cc830308502f8ad45bb0

See more details on using hashes here.

Provenance

The following attestation bundles were made for nuramem-0.1.0.tar.gz:

Publisher: release.yml on oaraya-hl/nuramem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nuramem-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nuramem-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 17.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nuramem-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 274c5f2efa449fc74d5cf43cac8eee8d495a51d37bb658f7c42aa16068e62aaa
MD5 8c76089ba9e6004084a70f388fa90e5b
BLAKE2b-256 05607df69f2afc28a40acede00d70a3b63970f481d88f6604e10f960291a00f3

See more details on using hashes here.

Provenance

The following attestation bundles were made for nuramem-0.1.0-py3-none-any.whl:

Publisher: release.yml on oaraya-hl/nuramem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page