Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,18 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SmartTasks
|
| 2 |
|
| 3 |
**Local-first desktop automation, powered by governance-validated AI.**
|
| 4 |
|
| 5 |
-
SmartTasks builds tools that keep humans in command of their workflows β and of the
|
| 6 |
-
AI those workflows increasingly rely on. Two things live here, tied together by the
|
| 7 |
-
models we publish on this page.
|
| 8 |
|
| 9 |
---
|
| 10 |
|
| 11 |
## π₯οΈ SmartTasks β Desktop Automation Platform
|
| 12 |
|
| 13 |
-
A no-code, **local-first** automation platform. Build powerful workflows with a
|
| 14 |
-
visual drag-and-drop builder, connect any desktop app, and run everything natively
|
| 15 |
-
on your own machine β full data privacy, no cloud upload required for execution.
|
| 16 |
|
| 17 |
- **Visual drag-and-drop builder** β triggers, actions, conditions, loops, sub-flows. No code.
|
| 18 |
- **14 core plugins + Marketplace** β AI Tools, Data Storage, Scheduler, HTTP, Email, Webhook, and more.
|
|
@@ -26,10 +31,7 @@ on your own machine β full data privacy, no cloud upload required for executio
|
|
| 26 |
|
| 27 |
## π‘οΈ IAIso β The Governance Framework
|
| 28 |
|
| 29 |
-
As automation platforms hand more decisions to autonomous AI, **IAIso** provides the
|
| 30 |
-
mechanical constraints that keep humans in command: hard-coded **system invariants**
|
| 31 |
-
AI cannot cross, and **human override** built into the decision circuit. It's the
|
| 32 |
-
governance layer behind everything we ship.
|
| 33 |
|
| 34 |
β [IAIso.org](https://iaiso.org) Β· [github.com/SmartTasksOrg/IAISO](https://github.com/SmartTasksOrg/IAISO)
|
| 35 |
|
|
@@ -37,11 +39,7 @@ governance layer behind everything we ship.
|
|
| 37 |
|
| 38 |
## π€ The Models on This Page
|
| 39 |
|
| 40 |
-
The GGUF models we publish here are the bridge between the two: **local AI, validated
|
| 41 |
-
against IAIso invariants**, ready to power SmartTasks automation privately and
|
| 42 |
-
on-device. Unlike a bare quantized re-upload, each ships with a documented,
|
| 43 |
-
machine-readable governance profile so you can decide whether a model is fit for an
|
| 44 |
-
autonomous loop *before* you wire it in:
|
| 45 |
|
| 46 |
- **Capability scorecard** β instruction-following, reasoning, structured output, and tool-calling, mapped to a capability tier (`scorecard.json`, machine-readable).
|
| 47 |
- **Red-team security assessment** β resistance to prompt-injection and jailbreak probes, reported honestly per attack class (weak spots included, not hidden).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: README
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: purple
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: static
|
| 7 |
+
pinned: false
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
# SmartTasks
|
| 11 |
|
| 12 |
**Local-first desktop automation, powered by governance-validated AI.**
|
| 13 |
|
| 14 |
+
SmartTasks builds tools that keep humans in command of their workflows β and of the AI those workflows increasingly rely on. Two things live here, tied together by the models we publish on this page.
|
|
|
|
|
|
|
| 15 |
|
| 16 |
---
|
| 17 |
|
| 18 |
## π₯οΈ SmartTasks β Desktop Automation Platform
|
| 19 |
|
| 20 |
+
A no-code, **local-first** automation platform. Build powerful workflows with a visual drag-and-drop builder, connect any desktop app, and run everything natively on your own machine β full data privacy, no cloud upload required for execution.
|
|
|
|
|
|
|
| 21 |
|
| 22 |
- **Visual drag-and-drop builder** β triggers, actions, conditions, loops, sub-flows. No code.
|
| 23 |
- **14 core plugins + Marketplace** β AI Tools, Data Storage, Scheduler, HTTP, Email, Webhook, and more.
|
|
|
|
| 31 |
|
| 32 |
## π‘οΈ IAIso β The Governance Framework
|
| 33 |
|
| 34 |
+
As automation platforms hand more decisions to autonomous AI, **IAIso** provides the mechanical constraints that keep humans in command: hard-coded **system invariants** AI cannot cross, and **human override** built into the decision circuit. It's the governance layer behind everything we ship.
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
β [IAIso.org](https://iaiso.org) Β· [github.com/SmartTasksOrg/IAISO](https://github.com/SmartTasksOrg/IAISO)
|
| 37 |
|
|
|
|
| 39 |
|
| 40 |
## π€ The Models on This Page
|
| 41 |
|
| 42 |
+
The GGUF models we publish here are the bridge between the two: **local AI, validated against IAIso invariants**, ready to power SmartTasks automation privately and on-device. Unlike a bare quantized re-upload, each ships with a documented, machine-readable governance profile so you can decide whether a model is fit for an autonomous loop *before* you wire it in:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
- **Capability scorecard** β instruction-following, reasoning, structured output, and tool-calling, mapped to a capability tier (`scorecard.json`, machine-readable).
|
| 45 |
- **Red-team security assessment** β resistance to prompt-injection and jailbreak probes, reported honestly per attack class (weak spots included, not hidden).
|