Get This Tool
Ciris
Pricing
- Model
- Free
Summary
Every AI conversation you have travels to a data center you don't control, logs you can't inspect, and infrastructure you're paying for with your privacy — CIRIS is built on the premise that none of that has to be true.
CIRIS runs a signed reasoning agent on your phone or a home device, with no warehouse in the middle for the closest privacy circles. The vendor describes two paths: fully on-device using a small model like Gemma 4, or free hosted inference for phones that can't run a local model — both paths produce cryptographically signed outputs. Every claim the agent makes carries an ed25519+post-quantum signature, so you can audit it, revoke trust, and re-open any conclusion built on a bad source. The architecture depends on a 'social circle' data model; data in your innermost circles never sends the network message that would let anyone request it. Teams needing broad third-party integrations or a hosted API endpoint will find neither here.
Bottom line: Pick CIRIS if your use case is a privacy-preserving personal assistant where auditable, revocable AI claims matter — hit a wall the moment you need an outbound API, enterprise identity management, or any integration outside the CEWP fabric.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- On-device inference with no data center in the path for supported hardware, which means your input and the agent's reasoning never leave the device — no logs elsewhere, no third-party retention.
- Cryptographic signing on every agent output using ed25519 plus a post-quantum scheme, so you can trace exactly what the agent claimed, who agreed, who pushed back, and revoke trust retroactively if a source is found to be misleading.
- Seven-circle privacy model where innermost circles are structurally isolated — not by policy enforcement but by the absence of the outbound network message — which means there is no configuration mistake that can accidentally expose 'self' or 'family' data.
- Fully open-source under AGPL-3.0 with self-hosted option, so the vendor going dark does not kill your deployment and you can audit the signing and isolation logic yourself.
- Hosted inference path available at no cost for low-resource devices in 29 languages, which means teams can deploy to users whose hardware cannot run a local model without building separate infrastructure.
Cons
Sign in to edit- No API surface exists — there is no endpoint to call from an external pipeline, no webhook, no SDK. Any team building a product that needs to programmatically query the agent or integrate it into an existing backend hits a hard wall on day one and moves to a tool with an API.
- The CEWP fabric is a closed trust network; it does not bridge to standard enterprise identity systems, cloud storage, or third-party data sources. Teams expecting to connect the agent to a CRM, a document store, or an external knowledge base find no integration path and either abandon the tool or build outside the CEWP model entirely.
- On-device inference requires hardware capable of running a small local model. The vendor names Gemma 4 as an example. Devices that cannot meet this threshold fall back to hosted inference, reintroducing a data center into the path and partially negating the core privacy architecture for those users.
- The social circle and trust federation model is novel and not documented against standard compliance frameworks. Teams operating under HIPAA, SOC 2, or GDPR audit requirements cannot map CIRIS's architecture to their compliance checklists without significant interpretive work — and no audit trail export to standard formats is described.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- iPhone, Android, desktop, pip
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-12T23:33:22.587Z
Best For
Who it's for
- Users seeking fully local AI without data centers
- Applications requiring auditable and revocable AI outputs
- Privacy-focused personal AI assistants
What it does well
- Local reasoning and decision making on personal devices
- Verifiable AI claims with cryptographic signing
- Privacy-preserving interactions within defined social circles
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Ciris
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Ciris free?
- Yes — Ciris is fully free to use. There is no paid tier.
- Is Ciris open source?
- Yes. Ciris is open source.
- Can I self-host Ciris?
- Yes. Ciris supports self-hosting on your own infrastructure.
- What platforms does Ciris support?
- Ciris is available on: iPhone, Android, desktop, pip.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Most AI assistants hand your input to a server, return an answer, and leave you with no record of the reasoning and no way to contest the output. CIRIS takes a different path: CIRISAgent is the app and reasoning layer you hold; CEWP (‘soup’) is the peer fabric running on hardware you already own. The agent classifies all data into seven social circles — from ‘self’ out to ‘Global Commons’ — and for the innermost circles, the system structurally prevents data from leaving by never emitting the network message that would allow a remote request. There is no promise to enforce; the absence of the message is the enforcement.
The differentiating feature is cryptographic claim signing. Every significant output the agent produces is signed with ed25519 plus a post-quantum component and published to a shared trace. If a source is later caught misleading, every claim that source ever signed becomes moot, and every conclusion built on those claims can be re-opened. The docs describe this as ‘catching a liar and having it all come undone’ — not a one-time model audit at training time, but a continuous, public accountability layer that runs while the agent operates.
This fits a narrow but well-defined use case: a personal AI assistant where the user needs full local control, verifiable outputs, and privacy enforced by architecture rather than policy. It breaks down fast outside that scope. There is no API surface — nothing to call from an external service or pipeline. The CEWP fabric is its own trust network, not a bridge to existing enterprise tooling. Teams building customer-facing products, multi-system automations, or anything requiring third-party data ingestion will need a different foundation entirely.
The project is open-source under AGPL-3.0, with code at github.com/CIRISAI. The vendor states App Store and Google Play availability. Hosted inference is available at no cost for devices that cannot run a local model, supporting 29 languages — the vendor notes this path does use a data center, but outputs remain signed by the same mechanism.