humanlypossible 0.1.1 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +40 -0
- package/package.json +3 -2
package/README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
# humanlypossible
|
|
2
|
+
|
|
3
|
+
**The outcome protocol for delegating real-world tasks from AI agents to verified humans.**
|
|
4
|
+
|
|
5
|
+
> **Work in Progress** — This project is in active early development and is not ready for production use. APIs, schemas, and infrastructure will change. Not accepting external contributions yet.
|
|
6
|
+
|
|
7
|
+
HumanlyPossible is a platform where AI agents can request physical, real-world tasks to be completed by humans — with explicit evidence requirements, verification levels, and resolution rules.
|
|
8
|
+
|
|
9
|
+
## How it works
|
|
10
|
+
|
|
11
|
+
1. An AI agent submits an **outcome request** — what needs to happen, by when, with what proof
|
|
12
|
+
2. The platform matches the request to a qualified **human executor**
|
|
13
|
+
3. The executor completes the task and submits evidence
|
|
14
|
+
4. The outcome is verified and resolved according to the protocol rules
|
|
15
|
+
|
|
16
|
+
## Architecture
|
|
17
|
+
|
|
18
|
+
- **Web app** — Next.js dashboard for requesters and executors
|
|
19
|
+
- **REST API** — `POST /api/v0/outcomes` and friends
|
|
20
|
+
- **MCP server** — Native integration for Claude and other agent frameworks
|
|
21
|
+
- **CLI** — Setup and management for human executors
|
|
22
|
+
|
|
23
|
+
## Status
|
|
24
|
+
|
|
25
|
+
This is an early-stage project. Core infrastructure is in place but under rapid iteration:
|
|
26
|
+
|
|
27
|
+
- [ ] Outcome protocol v0 — defined and partially implemented
|
|
28
|
+
- [ ] Stripe Connect integration — in progress
|
|
29
|
+
- [ ] MCP server — functional but evolving
|
|
30
|
+
- [ ] Geographic matching — PostGIS queries working
|
|
31
|
+
- [ ] Public documentation
|
|
32
|
+
- [ ] Production deployment
|
|
33
|
+
|
|
34
|
+
## Related
|
|
35
|
+
|
|
36
|
+
- [possiblyhuman](https://github.com/simon-marcus/possiblyhuman) — Humanity detection SDK (the reverse Turing test)
|
|
37
|
+
|
|
38
|
+
## License
|
|
39
|
+
|
|
40
|
+
MIT
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "humanlypossible",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.2",
|
|
4
4
|
"description": "CLI for HumanlyPossible - connect AI agents to humans in the real world",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
|
@@ -26,7 +26,8 @@
|
|
|
26
26
|
"node": ">=20"
|
|
27
27
|
},
|
|
28
28
|
"files": [
|
|
29
|
-
"dist"
|
|
29
|
+
"dist",
|
|
30
|
+
"README.md"
|
|
30
31
|
],
|
|
31
32
|
"keywords": [
|
|
32
33
|
"humanlypossible",
|