Skip to main content

AgenticMemory Python SDK (v0.2.0)

Python SDK for AgenticMemory -- portable binary graph memory for AI agents. 16 query types, zero dependencies.

Install

pip install agentic-brain

With LLM integrations

pip install agentic-brain[anthropic]   # Claude
pip install agentic-brain[openai]      # GPT
pip install agentic-brain[ollama]      # Local models
pip install agentic-brain[all]         # All providers

Quick Start

from agentic_memory import Brain

brain = Brain("my_agent.amem")
brain.add_fact("User is a Python developer", session=1)
brain.add_decision("Recommended FastAPI for REST APIs", session=1)

print(brain.facts())
print(brain.info())

v0.2 Query Expansion

Nine new methods added in v0.2.0:

brain = Brain("my_agent.amem")

# Retrieval
results = brain.search_text("API rate limit")           # BM25 (1.58 ms @ 100K)
results = brain.search("caching strategy", top_k=10)    # Hybrid BM25+vector (10.83 ms)

# Structural analysis
scores = brain.centrality(metric="pagerank")             # PageRank (34.3 ms @ 100K)
path   = brain.shortest_path(src=42, dst=99)             # BFS (104 us @ 100K)

# Cognitive reasoning
report  = brain.revise(node_id=42)                       # Counterfactual cascade (53.4 ms)
gaps    = brain.gaps()                                    # Find reasoning weaknesses
matches = brain.analogy(node_id=42, top_k=5)             # Structural pattern matching

# Graph maintenance
report = brain.consolidate(dry_run=True)                 # Dedup, contradiction linking
drift  = brain.drift()                                   # Belief evolution tracking (68.4 ms)

With LLM Integration

from agentic_memory import Brain, MemoryAgent
from agentic_memory.integrations import AnthropicProvider

brain = Brain("my_agent.amem")
agent = MemoryAgent(brain, AnthropicProvider())

response = agent.chat("My name is Alice. I work on ML systems.", session=1)
response = agent.chat("What do I work on?", session=2)

Test Coverage

104 tests across 8 modules, including 20 tests for the v0.2 query expansion methods.

Requirements

  • Python >= 3.10
  • amem binary (Rust core engine) -- install via cargo install agentic-memory

Documentation

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

agentic_brain-0.3.0.tar.gz (38.2 kB view details)

Uploaded Source

Built Distribution

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

agentic_brain-0.3.0-py3-none-any.whl (35.0 kB view details)

Uploaded Python 3

File details

Details for the file agentic_brain-0.3.0.tar.gz.

File metadata

  • Download URL: agentic_brain-0.3.0.tar.gz
  • Upload date:
  • Size: 38.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for agentic_brain-0.3.0.tar.gz
Algorithm Hash digest
SHA256 0d6a868f3c04977db15f895a3b61ac7fd7190bfb2d061d94dcebc9fcf5315cd7
MD5 9d414f08fce1a00723c00d5f36178c8d
BLAKE2b-256 3845414a4c20f1402c4887720fdd5927ba534274951cb591fc1580f447d014f2

See more details on using hashes here.

File details

Details for the file agentic_brain-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: agentic_brain-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 35.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for agentic_brain-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3f4c87398c06263a2573f92af3948da558dcd4c44927daa416d6b6033ab836c8
MD5 71cd498f3afd0e806e3200dad723df92
BLAKE2b-256 92b610d2caa3f44d8868ffecc6d9df13dc18570f5695823db766275c69abc980

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 files

0.2.1

2 files

0.2.0

2 files

0.1.0

2 files

Supported by

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