Eidet

eidet-sdk

Python client SDK for Eidet — long-term memory for AI coding agents.

Install

pip install eidet-sdk

Usage

from eidet_sdk import EidetClient, MemoryType

client = EidetClient()  # defaults to http://localhost:19380

# Store a memory
result = client.store(
    repo="/path/to/project",
    content="The auth module uses JWT with RS256 signing",
    type=MemoryType.OBSERVATION,
    tags=["auth", "jwt"],
)

# Search memories
results = client.recall("/path/to/project", "authentication")

# Get session context (L0 identity + L1 top memories, < 600 tokens)
context = client.context("/path/to/project")

# Browse all memories
page = client.browse("/path/to/project", skip=0, take=50)

# Feedback loop
client.feedback("memories/...", was_used=True)   # echo (useful)
client.feedback("memories/...", was_used=False)  # fizzle (irrelevant)

Context Manager

with EidetClient(url="http://localhost:19380") as client:
    results = client.recall("/path/to/project", "deployment")

API Key Authentication

client = EidetClient(url="http://localhost:19380", api_key="your-api-key")

All Methods

Method Description
store(repo, content, ...) Store a memory (observation, insight, procedure, heuristic; negative/valence for dead-ends, stage for subtask scoping)
recall(repo, query, **kwargs) Search memories by meaning and keywords (filters: type, tags, valence, stage, cross_repo)
context(repo) Get compact session context (< 600 tokens)
get_memory(id) Get a specific memory by ID (includes contentSha256 for optimistic concurrency)
update(memory_id, **kwargs) Update a memory (content changes create versions; expected_content_sha256 precondition)
redact(memory_id, reason) Scrub a memory's content to a tombstone
forget(id, reason?) Soft-delete a memory
feedback(memory_id, was_used) Echo (useful) or fizzle (irrelevant) feedback
history(id) Get version chain for a memory
browse(repo, **kwargs) Paginated memory listing
graph(repo, limit?) Graph data for visualization
repos() List all known repositories
intake(repo) Ingest project files as seed memories
intake_git(repo, **kwargs) Seed memories from git commit history
intake_claude_memory(repo, dry_run?) Import Claude Code's native per-project memory
consolidate(repo) Merge related observations into insights
maintenance(repo) Run maintenance pipeline
export_markdown(repo, format?) Export memories as markdown ("agents" for AGENTS.md shape)
health() Health check
status() Service status and stats
is_available() Check if the service is reachable

Requirements

  • Eidet service running locally (eidet serve or installed as system service)
  • Python 3.10+
  • httpx

License

MIT

Project links

Data verified by PyPI on
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.11.3)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for stevehansen from gravatar.com stevehansen

GitHub Statistics

Data verified by PyPI on 
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT

Requires

Python >=3.10

Tags

eidet memory ai coding-agent mcp

Report project as malware

Download files

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

Source Distribution

eidet_sdk-0.10.0.tar.gz (5.4 kB view details)

Uploaded Source

Built Distribution

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

eidet_sdk-0.10.0-py3-none-any.whl (5.9 kB view details)

Uploaded Python 3

File details

Details for the file eidet_sdk-0.10.0.tar.gz.

File metadata

  • Download URL: eidet_sdk-0.10.0.tar.gz
  • Upload date:
  • Size: 5.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for eidet_sdk-0.10.0.tar.gz
Algorithm Hash digest
SHA256 41780684400d8b0be4ff19f767f3da6b41d6b4a0915bd20e62f44bc69ce55233
MD5 fb50999fd6e854d210fe6e1b9daab5ce
BLAKE2b-256 d35d03edcf77e0e86bcedf57bd64d0699f60c661bcbf8d4fb5345eb67d327e05

See more details on using hashes here.

Provenance

The following attestation bundles were made for eidet_sdk-0.10.0.tar.gz:

Publisher: release.yml on stevehansen/eidet

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

File details

Details for the file eidet_sdk-0.10.0-py3-none-any.whl.

File metadata

  • Download URL: eidet_sdk-0.10.0-py3-none-any.whl
  • Upload date:
  • Size: 5.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for eidet_sdk-0.10.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1ec0805d326fda43f40182bdfdadc5b4898c9ceae6f672d1e0d07aa1a228aec7
MD5 df703103a9ffe442f878cbe07dedaf8d
BLAKE2b-256 c76ab3c24afc72319a96b2aa17e5c9b183e0917d9e7fa5e202560a71648f768e

See more details on using hashes here.

Provenance

The following attestation bundles were made for eidet_sdk-0.10.0-py3-none-any.whl:

Publisher: release.yml on stevehansen/eidet

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