Skip to main content

CogmemAi Python SDK

The smart memory layer for everything Ai. Persistent, encrypted recall for any Ai system: agents, assistants, robots, and the tools you already use. 95.10% on LongMemEval, the highest published score.

Install

pip install cogmemai

Quick Start

from cogmemai import CogmemAi

client = CogmemAi("cm_your_api_key_here")

# Save a memory
client.save_memory(
    content="This project uses React with TypeScript",
    memory_type="architecture",
    category="frontend",
    importance=8,
)

# Search memories
results = client.recall_memories("what framework does this project use?")
for memory in results["memories"]:
    print(f"[{memory['importance']}] {memory['content']}")

# Load project context
context = client.get_project_context(project_id="my-project")

# Extract memories from conversation
client.extract_memories(
    user_message="Let's use PostgreSQL for the database",
    assistant_response="Good choice. I'll set up the schema with...",
)

All Methods

Core Memory

  • save_memory(content, memory_type, category, subject, importance, scope, project_id), Save a memory
  • recall_memories(query, limit, memory_type, scope), Semantic search
  • extract_memories(user_message, assistant_response, previous_context), Ai extracts facts from conversation
  • get_project_context(project_id, include_global, context), Load top memories with smart ranking
  • list_memories(memory_type, category, scope, limit, offset), Browse with filters
  • update_memory(memory_id, content, importance, scope), Edit a memory
  • delete_memory(memory_id), Delete permanently
  • get_usage(), Check usage stats and tier

Documents & Sessions

  • ingest_document(text, document_type, project_id), Extract memories from docs
  • save_session_summary(summary, project_id), Capture session accomplishments

Import / Export

  • export_memories(), Back up memories as JSON
  • import_memories(memories), Bulk import from JSON
  • get_memory_versions(memory_id), Version history

Team & Collaboration

  • get_team_members(project_id), List team members
  • invite_team_member(email, project_id, role), Invite a member
  • remove_team_member(member_id), Remove a member

Memory Relationships & Promotion

  • link_memories(memory_id, related_memory_id, relationship_type), Link related memories
  • get_memory_links(memory_id), Get linked memories
  • get_promotion_candidates(), Find cross-project patterns
  • promote_to_global(memory_id), Promote to global scope

Error Handling

from cogmemai.client import CogmemAiError

try:
    client.save_memory(content="test")
except CogmemAiError as e:
    print(f"Error {e.status_code}: {e}")

Get an API Key

  1. Sign up at hifriendbot.com/developer/
  2. Generate an API key
  3. Start saving memories

Metadata

Release files for cogmemai 1.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cogmemai 1.1.0
File Size Uploaded
cogmemai-1.1.0.tar.gz 6.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for cogmemai 1.1.0
File Interpreter ABI Platform
cogmemai-1.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 14.8 kB

Release files / cogmemai-1.1.0.tar.gz

Download URL cogmemai-1.1.0.tar.gz
Size 6.8 kB
Tags Source
SHA-256 checksum
How to use checksums
2c7e8255f804ddbd0ecae2d5190f81be0a821b5647068e747cfd34fd69ee61bd
BLAKE2b-256 checksum
How to use checksums
b785d19df94a3db8f0ea738da4a49b2e488f4760fcab8fbfddcb815b563dffc2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.0

Release files / cogmemai-1.1.0-py3-none-any.whl

Download URL cogmemai-1.1.0-py3-none-any.whl
Size 8.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3cf213e95f23f95896f78f336c8ea1bdd830654a540e0b347f407e2f4667ef15
BLAKE2b-256 checksum
How to use checksums
eec0260e427695a2f52e55b50a2866f5fde9f4f2bb4322123ab3fd1c3cb87af5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.0

Release history Release notifications | RSS feed

1.1.1

2 release files

This release

1.1.0 This release

2 release files

1.0.2

2 release files

1.0.1

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page