This release is a pre-release and may not be stable for production use.
Redis Iris
One package for every Iris product: an opinionated Python API per product, and the iris CLI to set them all up.
Install
Requires Python 3.11+. uv is the recommended installer.
uv add redis-iris # library, in your project
uv tool install redis-iris # iris CLI, isolated
iris --help
pipx or pip
pipx install redis-iris
python -m pip install redis-iris # inside an active virtual environment
From a source checkout, uv tool install --force . installs or replaces the iris tool, and
python -m redis_iris runs the CLI wherever the package is installed.
Alpha releases may change commands and output contracts. Pin a version in automation and check the release notes before upgrading.
The stack
Iris is a suite of products. Use one, or all of them.
| Product | What your agent gets | Instead of |
|---|---|---|
| Agent Memory | Ordered session history, summarized automatically. Durable memories extracted in the background, typed to your domain and steered away from sensitive data. Recall across sessions, scoped to one customer plus shared team knowledge. Erase a customer in one call. | an in-process store, a hand-built extraction chain, regex scrubbing |
| Playbook | Answers only from published, versioned FAQs and Skills, scored. Rollback and withdrawal. Proposes an FAQ for human review when nothing covers the question. | a vector store of unreviewed policy docs |
| Context Retriever (coming soon) | Typed MCP tools generated from your data model: get, filter, search, per entity. Read-only agent keys scoped to one surface. Your Redis data stays where it is. | hand-written @tool functions over your database |
| Lens (client publishing soon) | One trace per turn: which memories and documents entered the prompt, tokens, cost. | guessing why the agent said that |
User guides
| Your agent... | Guide | Product |
|---|---|---|
| forgets customers between sessions | Remember customers | Agent Memory |
| quotes policy nobody approved | Answer from approved policy | Agent Playbook |
| needs live account data, not documents | Live account data | Context Retriever |
| needs all three in one message | One support turn | Iris |
| needs to be configured | Configuration | all |
| needs an Agent Memory service created | Set up Agent Memory | Agent Memory |
| needs a Playbook and an agent key created | Set up Agent Playbook | Agent Playbook |
| has policy content to author and publish | Agent Playbook CLI | Agent Playbook |
Integrate with an existing agent
Built your stack with a popular orchestration tool? A skill lets your coding agent do the wiring.
| I want my agent to... | Skill |
|---|---|
| figure out what it needs | add-redis-iris |
| remember customers | add-agent-memory |
| quote approved policy only | add-agent-playbook |
| use live account data | add-context-retriever |
The CLI
iris <product> <command> creates services, mints keys, and manages content. Shared options go
before the product name.
iris agent-memory service create --from service.yaml --write-env .env
iris agent-memory service key <store-id> --actions read --name inspector --write .env.inspector
iris agent-memory memories search "how does this customer want answers" --owner cust-1042 --prompt
iris agent-playbook extraction bind <store-id> --idle-seconds 60 --enable # FAQ proposals from sessions
iris agent-playbook faqs validate ./faqs # offline
iris agent-playbook faqs sync ./faqs --publish changed
iris --json --no-input agent-playbook faqs plan ./faqs # unattended, one JSON value on stdout
iris --profile production agent-playbook health
Settings resolve from command options, environment variables, the selected TOML profile, shared
TOML settings, then defaults. API keys belong in environment variables. Exit codes are 0 for
success, 1 for operational failures, and 2 for invalid input or configuration. Help, version,
completion, and local validation work without credentials or a network connection.
Guides: Set up Agent Memory, Set up Agent Playbook, Agent Playbook CLI, Configuration, example TOML.
Documentation
The docs are internal: read them in docs/, or render the site locally with task docs:serve.
| Resource | Start here to... |
|---|---|
| Core reference | Every redis_iris class and setting |
| User guides | One problem, one fix, per product |
| Skills | Wire a product into an existing agent with a coding agent |
| llms.txt | task docs:build writes site/llms.txt; hand that one file to a coding agent |
| Design | What the package is, and why it is shaped this way |
| Release notes | Check changes before upgrading |
Contributing
Bug reports, documentation improvements, and new integrations are welcome. Open an issue or read the contributor guide.
task install
task check # formatting, lint, types, offline tests, package build
Maintainers publish with the release runbook.
License
MIT.
Metadata
Release files for redis-iris 0.1.0a3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| redis_iris-0.1.0a3.tar.gz | 578.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| redis_iris-0.1.0a3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 725.4 kB
Release files / redis_iris-0.1.0a3.tar.gz
| Download URL | redis_iris-0.1.0a3.tar.gz |
|---|---|
| Size | 578.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
04e453fa2c47a42409015647308e9f8be78c9414278999cdecbb9a424364c664
|
|
BLAKE2b-256 checksum How to use checksums |
8f773af4bcb263047bd3500e9cdce877eaee55136570e3ba618ee8fc2476763d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / redis_iris-0.1.0a3-py3-none-any.whl
| Download URL | redis_iris-0.1.0a3-py3-none-any.whl |
|---|---|
| Size | 147.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
63d1ec64613055b94904f7d437c287a990ebfaf0ecad193b53ee51aff976f264
|
|
BLAKE2b-256 checksum How to use checksums |
c6cedacbcbabbfb8db25d01758a387b2e3295af3c6b9eac7316722ad2bde62aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|