cortex-memory

Persistent memory engine for AI agents. Local-first, sub-millisecond, zero cloud.

Native Python binding for Cortex — a Rust memory engine with 4-tier memory, Bayesian beliefs, people graph, and HNSW vector search.

Install

pip install cortex-ai-memory

Quick Start

from cortex_python import PyCortex

# Open or create a memory database
cx = PyCortex("memory.db")

# Ingest memories
cx.ingest("Met Alice at the Q3 planning meeting", "slack", user_id="alice_123")
cx.ingest("User prefers dark mode", "cli")

# Retrieve relevant memories
results = cx.retrieve("What do I know about Alice?", limit=5)
for memory_id, score, text in results:
    print(f"[{score:.2f}] {text}")

# Generate LLM-ready context (token-budgeted)
context = cx.get_context(2000, channel="slack")

# Structured knowledge
cx.add_fact("Alice", "works_at", "Acme Corp", 0.95, "slack")
cx.add_preference("timezone", "Asia/Shanghai", 0.9)

# Bayesian beliefs
cx.observe_belief("user_likes_python", True, 0.8)
beliefs = cx.get_beliefs(0.5)

# People graph
cx.add_person("Alice", "slack", "alice_123")

# Consolidation (run periodically)
scanned, promoted, swept, patterns = cx.run_consolidation()

With Embeddings

For semantic search, pass embeddings from any provider:

import numpy as np

# Use any embedding model (OpenAI, ollama, sentence-transformers, etc.)
def embed(text):
    # your embedding function here
    ...

cx.ingest("I live in Shanghai", "cli", embedding=embed("I live in Shanghai"))
results = cx.retrieve("where do I live?", 5, embedding=embed("where do I live?"))

Features

4-tier memory: Working, Episodic, Semantic, Procedural
HNSW vector search: Sub-millisecond at 100K+ memories
Bayesian beliefs: Self-correcting with evidence
People graph: Cross-channel identity resolution
Conversation compression: Automatic session summarization
Contradiction detection: Catches conflicting facts
Chinese + English: Native bilingual NLP
Zero cloud: 100% local, your data stays on your device
3.8MB binary: Pure Rust, zero runtime dependencies

License

MIT

Download files

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

Source Distribution

cortex_ai_memory-2.2.0.tar.gz (211.2 kB view details)

Uploaded Jun 14, 2026 Source

Built Distributions

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl (1.5 MB view details)

Uploaded Jun 14, 2026 CPython 3.12macOS 11.0+ ARM64

cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB view details)

Uploaded Jun 14, 2026 CPython 3.9manylinux: glibc 2.17+ x86-64

File details

Details for the file cortex_ai_memory-2.2.0.tar.gz.

File metadata

Download URL: cortex_ai_memory-2.2.0.tar.gz
Upload date: Jun 14, 2026
Size: 211.2 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cortex_ai_memory-2.2.0.tar.gz
Algorithm	Hash digest
SHA256	`78ace06646cc99b608c3ce7779d808c5f4422a79e5d403092cbb121c53359ad4`
MD5	`5b5a6533b45722f3b83398a456674beb`
BLAKE2b-256	`975256b0c365f3c1315ed9b6ceb854d69f0b40bfe98ae60229a6a33211015bcc`

See more details on using hashes here.

Provenance

The following attestation bundles were made for cortex_ai_memory-2.2.0.tar.gz:

Publisher: release-python.yml on gambletan/cortex

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: cortex_ai_memory-2.2.0.tar.gz
- Subject digest: 78ace06646cc99b608c3ce7779d808c5f4422a79e5d403092cbb121c53359ad4
- Sigstore transparency entry: 1820662594
- Sigstore integration time: Jun 14, 2026
Source repository:
- Permalink: gambletan/cortex@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Branch / Tag: refs/tags/v2.2.0
- Owner: https://github.com/gambletan
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release-python.yml@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Trigger Event: push

File details

Details for the file cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

Download URL: cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl
Upload date: Jun 14, 2026
Size: 1.5 MB
Tags: CPython 3.12, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`b39540defa6007e8707add0788e4a0961416c92c094bc048f6c891ea14a767b0`
MD5	`6dcbd4300f5d36c7b61dba40a3396c49`
BLAKE2b-256	`1421e778fea0ebe096eddd86ecc420a1c0c4d585b13da0f61d7d5515d0f9c28f`

See more details on using hashes here.

Provenance

The following attestation bundles were made for cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl:

Publisher: release-python.yml on gambletan/cortex

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: cortex_ai_memory-2.2.0-cp312-cp312-macosx_11_0_arm64.whl
- Subject digest: b39540defa6007e8707add0788e4a0961416c92c094bc048f6c891ea14a767b0
- Sigstore transparency entry: 1820662740
- Sigstore integration time: Jun 14, 2026
Source repository:
- Permalink: gambletan/cortex@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Branch / Tag: refs/tags/v2.2.0
- Owner: https://github.com/gambletan
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release-python.yml@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Trigger Event: push

File details

Details for the file cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Jun 14, 2026
Size: 1.7 MB
Tags: CPython 3.9, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`cb6694737e2cb8d357797fe01b6062b1868115b44343729303c73884f347109e`
MD5	`bfd2381a52331498c5223c5fe39473f9`
BLAKE2b-256	`f59de17f75c7438ce2988328c8c2c85d558924b52556e1b2f03c2fd71e984318`

See more details on using hashes here.

Provenance

The following attestation bundles were made for cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: release-python.yml on gambletan/cortex

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

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: cortex_ai_memory-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: cb6694737e2cb8d357797fe01b6062b1868115b44343729303c73884f347109e
- Sigstore transparency entry: 1820662916
- Sigstore integration time: Jun 14, 2026
Source repository:
- Permalink: gambletan/cortex@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Branch / Tag: refs/tags/v2.2.0
- Owner: https://github.com/gambletan
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release-python.yml@6c41b5d8ee6ffc70ab1db70ee033a6a3591de88f
- Trigger Event: push

Release history Release notifications | RSS feed

This release

2.2.0 This release

Jun 14, 2026 3 files

1.3.0

Mar 11, 2026 4 files

1.0.0

Mar 11, 2026 3 files

cortex-ai-memory 2.2.0

cortex-memory

Install

Quick Start

With Embeddings

Features

License

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License expression

Requires

Tags

Classifiers

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

Release history Release notifications | RSS feed