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
uv projects on an alpha release. uv takes a pre-release only when your own project names it,
and an alpha redis-iris pins product SDK pre-releases exactly, so uv add fails with
hint: pre-releases weren't enabled. Restate this release's pre-release pins in your
pyproject.toml (they are the == pre-release entries in its dependencies and change with each
release):
[tool.uv]
constraint-dependencies = [
"redis-agent-memory==0.5.0b2",
"redis-agent-playbook==0.1.0b2",
"redis-context-gateway==0.1.0a6",
"redis-intent-router==0.1.0a1",
]
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 |
| Agent Playbooks | 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 Gateway | One MCP endpoint and one agent key for every MCP server and Context Surface. Per-tool cache, and compression: large results as handles the agent pages through. | a config entry and a secret per MCP server in every agent |
| Intent Router | The user's prompt matched to one of the intents you defined, with its score and the dispatch target you attached. | a prompt classifier you tune by hand, or an LLM call per routing decision |
| Lens | 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 Playbooks |
| 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 Playbooks | Agent Playbooks |
| has policy content to author and publish | Agent Playbooks CLI | Agent Playbooks |
| needs a Context Gateway to reach its tools | Context Gateway CLI | Context Gateway |
| needs to route a prompt to an intent | Intent Router CLI | Intent Router |
| needs to list, revoke or rotate agent keys | Identity CLI | Every product |
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-playbooks |
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-playbooks extraction bind <store-id> --idle-seconds 60 --enable # FAQ proposals from sessions
iris agent-playbooks faqs validate ./faqs # offline
iris agent-playbooks faqs sync ./faqs --publish changed
iris --json --no-input agent-playbooks faqs plan ./faqs # unattended, one JSON value on stdout
iris --profile production agent-playbooks health
iris --json context-gateway service list # Context Gateway control plane
iris intent-router service create support --provider openai --model text-embedding-3-small \
--dimensions 1536 --write-env .env
iris identity keys list --product intent # agent keys, for every product
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 Playbooks, Agent Playbooks CLI, Context Gateway CLI, Intent Router CLI, Identity CLI, Configuration, example TOML.
Upgrading to Agent Playbooks
The product is now Agent Playbooks; a Playbook is one instance. This follows the core SDK. Old
environment variables and the old TOML table are still read as fallbacks, so existing .env
files and TOML keep working; the CLI writes only the new names. iris agent-playbook stops with
a pointer to the new group, and the Python names have no aliases.
| Before | Now |
|---|---|
iris agent-playbook |
iris agent-playbooks |
IRIS_AGENT_PLAYBOOK_ID |
IRIS_AGENT_PLAYBOOKS_PLAYBOOK_ID |
IRIS_AGENT_PLAYBOOK_* (URL, API_KEY, CONTENT_API_KEY, SERVICE_URL, ...) |
IRIS_AGENT_PLAYBOOKS_* |
TOML [agent_playbook], [profiles.<name>.agent_playbook] |
[agent_playbooks], [profiles.<name>.agent_playbooks] |
redis_iris.agent_playbook, AgentPlaybook, AgentPlaybookSettings |
redis_iris.agent_playbooks, AgentPlaybooks, AgentPlaybooksSettings |
IrisSettings.agent_playbook, Iris.agent_playbook() |
IrisSettings.agent_playbooks, Iris.agent_playbooks() |
A new variable wins over its old name; set it empty to ignore the old one. The old TOML table is read only when the new one is absent.
Documentation
Read the docs 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 |
| 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: releases are described in the contributor guide.
License
MIT.
Metadata
Release files for redis-iris 0.1.0a8
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 |
|---|---|---|---|---|
| redis_iris-0.1.0a8.tar.gz | 962.4 kB | Without provenance | Details for redis_iris-0.1.0a8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| redis_iris-0.1.0a8-py3-none-any.whl | Python 3 | none | any | Details for redis_iris-0.1.0a8-py3-none-any.whl |
Total release size: 1.3 MB
Release files / redis_iris-0.1.0a8.tar.gz
| Download URL | redis_iris-0.1.0a8.tar.gz |
|---|---|
| Size | 962.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e55feb40a44980b618b118282d56368a07f88c84c7a35f08951f1da25f76efb7
|
|
BLAKE2b-256 checksum How to use checksums |
0f6672606d037336eeacf05611a988f9e16d00f0a660727de3f5b50bae53e4ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Release files / redis_iris-0.1.0a8-py3-none-any.whl
| Download URL | redis_iris-0.1.0a8-py3-none-any.whl |
|---|---|
| Size | 344.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4723a8d1ef83b704f9e8241331f1c9996b747f76c128290611893a6ba0d9800b
|
|
BLAKE2b-256 checksum How to use checksums |
e7e4602c858e9883892bfaa6e0594583e5c42ef9a5d911a1d992c6b3fea0f987
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Security for redis-iris 0.1.0a8
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.