Agentic AI Comparison:
Project Alice vs Tendi AI
vs
Introduction
Project Alice and Tendi AI are assessed for their documented purposes, access, cost clarity and integrations. Project Alice is a legacy developer-managed voice/home assistant with event skills; Tendi v2 is a current mobile financial coach. Compare the actual home-device versus household-planning purpose and setup, not a universal agent ranking.
Overview
Project Alice
Project Alice is a GPL-3.0 modular voice/home-automation assistant using skills and events such as user requests or sensor changes.
Source remains accessible and not archived, with last push December 2023. Developer-managed Linux/Raspberry Pi, voice and skill setup require maintenance review.
Source access does not include free hardware, hosting or optional cloud speech/provider usage. Assess maintenance and deployment costs before adopting the source.
Docs/source describe skills, events, satellites, a web interface and API paths. Local processing depends on chosen engines; optional cloud speech means the deployment is not wholly offline.
Tendi AI
Tendi v2 is an educational household-finance app with financial-health calculations, debt payoff scenarios, weekly missions, family planning and a local coach. Its App Store release describes on-device PDF/camera/CSV statement import and categorization; it does not execute bank transfers or investment decisions.
The exact App Store listing links tendi.ai and describes a from-scratch reboot for iPhone/iPad with no bank login, Tendi account or server. The website returned a database error on repeated checks; current web access is unresolved, while the mobile listing remains accessible.
The store lists free access with in-app purchases, first-month-free membership and displayed Tendi Plus $3.99, Family $6.99 and Power $9.99. Billing cycles, regional totals and selected entitlements must be confirmed in-app; no fixed monthly price is inferred.
The developer documents Apple Intelligence on supported devices with a deterministic fallback and local document inputs. The old 12,000-bank connection claim is not current v2 support. Ask Tendi about API or webhook access before planning a custom integration.
Editorial ratings · 1–10, higher is better
These scores express our judgement of the cited product facts. They are not measured performance benchmarks. Each product is assessed for its stated purpose; a higher score does not make different workflows interchangeable.
Evidence gaps lower confidence and affect the relevant judgement. Unknown pricing does not mean free access. Research prototypes and retired products retain their historical scope, with adoption ratings reflecting current access.
Ratings assessed: 2026-10-09. Source verification dates may differ.
Documented capability: How useful and complete is the documented workflow for the product's stated purpose?
- 1–2: No usable current workflow established, or only an unsupported promise.
- 3–4: Historical, experimental or very limited workflow; substantial delivery gaps.
- 5–6: Concrete but narrow workflow, or promising research requiring specialist review.
- 7–8: Substantial documented end-to-end workflow with useful controls or customization.
- 9–10: Exceptionally complete documented scope and controls; reserve 10 for unusually strong evidence.
Ease of adoption: Can the intended user obtain and set up a usable product today?
- 1–2: Discontinued, unavailable, waitlisted, or no usable deployment path verified.
- 3–4: Archived software, restricted research/preorder access or uncertain current service access.
- 5–6: Developer-managed setup, significant configuration or sales-led implementation.
- 7–8: Active accessible product with manageable setup for its intended user.
- 9–10: Straightforward self-service access and setup, with unusually few adoption obstacles.
Value and cost clarity: How attractive and understandable is the cost model for the documented use?
- 1–2: No current purchasable or usable offer; historical prices cannot support a purchase.
- 3–4: Material price, entitlement, license or availability uncertainty limits budgeting.
- 5–6: Plausible value with custom pricing, significant setup costs or incomplete selected-plan terms.
- 7–8: Useful scope with clear entry pricing/allowances or accessible source, while accounting for running costs.
- 9–10: Exceptionally accessible and clear cost model for substantial useful scope; never assume free compute.
Integration options: How useful and extensible are the verified user-facing connections for the intended workflow?
- 1–2: No current user-facing connection verified, or former connections are unavailable.
- 3–4: Inputs/exports or one focused connection; internal dependencies are not native connectors.
- 5–6: Useful API, configurable tools or several relevant connections, with limited verified breadth.
- 7–8: Broad relevant connections or an extensible documented API/MCP/tool ecosystem.
- 9–10: Extensive documented ecosystem with multiple connection mechanisms and strong task relevance.
Metrics Comparison
Documented capability
Project Alice: 6/10
Evidence confidence: high
Editorial judgement 6/10: Project Alice is a GPL-3.0 modular voice/home-automation assistant using skills and events such as user requests or sensor changes.
Tendi AI: 7/10
Evidence confidence: high
Editorial judgement 7/10: Tendi v2 is an educational household-finance app with financial-health calculations, debt payoff scenarios, weekly missions, family planning and a local coach. Its App Store release describes on-device PDF/camera/CSV statement import and categorization; it does not execute bank transfers or investment decisions.
Project Alice is a legacy developer-managed voice/home assistant with event skills; Tendi v2 is a current mobile financial coach. Compare the actual home-device versus household-planning purpose and setup, not a universal agent ranking.
Ease of adoption
Project Alice: 4/10
Evidence confidence: high
Editorial judgement 4/10: Source remains accessible and not archived, with last push December 2023. Developer-managed Linux/Raspberry Pi, voice and skill setup require maintenance review.
Tendi AI: 7/10
Evidence confidence: medium
Editorial judgement 7/10: The exact App Store listing links tendi.ai and describes a from-scratch reboot for iPhone/iPad with no bank login, Tendi account or server. The website returned a database error on repeated checks; current web access is unresolved, while the mobile listing remains accessible.
Current accessible deployment and human setup are distinct from historical capability.
Value and cost clarity
Project Alice: 6/10
Evidence confidence: medium
Editorial judgement 6/10: Source access does not include free hardware, hosting or optional cloud speech/provider usage. Assess maintenance and deployment costs before adopting the source.
Tendi AI: 6/10
Evidence confidence: medium
Editorial judgement 6/10: The store lists free access with in-app purchases, first-month-free membership and displayed Tendi Plus $3.99, Family $6.99 and Power $9.99. Billing cycles, regional totals and selected entitlements must be confirmed in-app; no fixed monthly price is inferred.
Compare included usage, required subscriptions and running costs for your intended workload.
Integration options
Project Alice: 6/10
Evidence confidence: high
Editorial judgement 6/10: Docs/source describe skills, events, satellites, a web interface and API paths. Local processing depends on chosen engines; optional cloud speech means the deployment is not wholly offline.
Tendi AI: 3/10
Evidence confidence: high
Editorial judgement 3/10: The developer documents Apple Intelligence on supported devices with a deterministic fallback and local document inputs. The old 12,000-bank connection claim is not current v2 support. Ask Tendi about API or webhook access before planning a custom integration.
Check the connections required for your workflow, including plan access and setup.
Conclusions
Project Alice is a legacy developer-managed voice/home assistant with event skills; Tendi v2 is a current mobile financial coach. Compare the actual home-device versus household-planning purpose and setup, not a universal agent ranking. Ratings are subjective editorial opinions, not measured accuracy, safety, reliability, popularity or scientific benchmarks.
The best framework is the one you can keep current and afford to run.
Run OpenClaw or Hermes with saved memory, one-click runtime updates, and your choice of Platform Credits, provider keys, or supported subscriptions.
Plans start at $199/month. Cancel anytime.
Hosted agent
OpenClaw or Hermes