kagura-agent
A memory-backed autonomous AI agent. It combines a pluggable agentic brain,
Kagura Memory Cloud, a Docker security
membrane, and a Slack/Discord cockpit. Use it from the CLI with run, repl,
serve, doctor, and setup.
The default brain is Claude through the
Claude Agent SDK for Python. The optional
kagura-brain backend adds Claude,
Codex, and Ollama-compatible providers behind the same interface.
Status: alpha, package version
0.7.1. The v0.1–v0.7 pure-Python skeleton is implemented and tested with strict typing and at least 95% coverage. Live Docker, cloud credential, and chat-transport edges remain deployment-specific.
Why kagura-agent
- Persistent memory: decisions, failures, and progress survive individual runs.
- Real hands: filesystem, shell, Git, Docker, cloud APIs, and custom MCP tools.
- Bounded autonomy: credentials, mounts, and egress are granted per task.
- Operator control: long-running work can be launched, resumed, approved, or stopped from a CLI or chat cockpit.
Quickstart
You need Python 3.11 or newer, a Kagura Memory Cloud login, and a configured brain. The base package intentionally ships without a brain dependency.
python -m venv .venv
# Activate the virtual environment, then install the default brain:
pip install 'kagura-agent[claude]'
# Authenticate both required services:
kagura auth login
claude
# Verify the environment and run a task:
kagura-agent doctor
kagura-agent run "summarize the repository layout"
ANTHROPIC_API_KEY can replace the Claude subscription login. For the
kagura-brain Claude/Codex/Ollama backend, chat transports, Docker mode, Windows
activation, and first-run troubleshooting, see
Getting started.
Main commands
| Command | Purpose |
|---|---|
kagura-agent run "…" |
Run one task |
kagura-agent repl |
Continue an interactive session |
kagura-agent serve --transport slack |
Start the chat cockpit |
kagura-agent doctor |
Check memory, brain, Docker, and provider readiness |
kagura-agent setup transport |
Show transport setup guidance |
Architecture at a glance
The session layer orchestrates tasks and checkpoints without depending on a specific model SDK. The selected brain owns its agentic tool loop; Kagura Memory Cloud provides durable context; the host-side membrane controls filesystem, network, and credential access.
The full rationale, provider boundary, capability model, security membrane, and cockpit protocol live in the design document.
Documentation
| Document | Contents |
|---|---|
| Documentation index | Map of all project documentation |
| Getting started | Installation, authentication, commands, bootstrap, troubleshooting |
| Design | Scope, architecture, capabilities, security membrane, cockpit internals |
| Project status and scope | Current boundary, roadmap, repository map, milestone coverage |
| Extending | Custom MCP tools, egress, credential leasing, secret handling |
| Operations | Incident response and credential rotation runbooks |
| Bootstrap evaluation | Ranking evaluation and rollout gate |
| Legal notes | Open terms-of-service and operator-responsibility questions |
| Contributing | Development workflow and contribution guide |
| Security policy | Supported versions and vulnerability reporting |
| Changelog | Release history |
Development
git clone https://github.com/kagura-ai/kagura-agent.git
cd kagura-agent
pip install -e '.[dev]'
pytest
mypy
See CONTRIBUTING.md for the full development workflow.
Related repositories
| Repository | Role |
|---|---|
kagura-ai/kagura-engineer |
Independent coding-specialized sibling agent |
kagura-ai/kagura-code-reviewer |
Review subagent used by kagura-engineer |
kagura-ai/memory-cloud |
Persistent memory backbone and MCP server |
kagura-ai/kagura-memory-python-sdk |
Trusted-host bootstrap SDK |
License
Apache License 2.0 — © 2026 Kagura AI. See NOTICE for attribution.
Metadata
Release files for kagura-agent 0.7.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| kagura_agent-0.7.1.tar.gz | 599.9 kB | With provenance | Details for kagura_agent-0.7.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| kagura_agent-0.7.1-py3-none-any.whl | Python 3 | none | any | Details for kagura_agent-0.7.1-py3-none-any.whl |
Total release size: 813.0 kB
Release files / kagura_agent-0.7.1.tar.gz
| Download URL | kagura_agent-0.7.1.tar.gz |
|---|---|
| Size | 599.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9d949febbb729c8b4554de9b00dbe5e52cd9b947034013fc58e1bb55081a763e
|
|
BLAKE2b-256 checksum How to use checksums |
9ad1fcb2d777b5efd2854c362411e0b966733a552ab884d3f428ab4a76fa48a9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 24, 2026.
Transparency logRelease files / kagura_agent-0.7.1-py3-none-any.whl
| Download URL | kagura_agent-0.7.1-py3-none-any.whl |
|---|---|
| Size | 213.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8be2e6ec810183b8204bdbd16c528813f01d84b2891ec3888efe14e4d777c0eb
|
|
BLAKE2b-256 checksum How to use checksums |
a9f031252cc23c0390b02254f35e0108509f96e1cbdedb277bf45a46c28d5018
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 24, 2026.
Transparency logSecurity for kagura-agent 0.7.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for kagura_agent-0.7.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 24, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.