aether-colony 5.3.1 → 5.3.2
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 +14 -30
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,18 +1,10 @@
|
|
|
1
1
|
<div align="center">
|
|
2
2
|
|
|
3
|
-
<
|
|
4
|
-
|
|
5
|
-
<picture>
|
|
6
|
-
<source media="(prefers-color-scheme: dark)" srcset="./AetherLogo.png" />
|
|
7
|
-
<source media="(prefers-color-scheme: light)" srcset="./AetherLogo.png" />
|
|
8
|
-
<img src="./AetherLogo.png" alt="Aether" width="240" />
|
|
9
|
-
</picture>
|
|
10
|
-
|
|
11
|
-
<br>
|
|
3
|
+
<img src="./AetherBanner.png" alt="Aether" width="100%" />
|
|
12
4
|
|
|
13
5
|
# Aether
|
|
14
6
|
|
|
15
|
-
|
|
7
|
+
**Artificial Ecology for Thought and Emergent Reasoning**
|
|
16
8
|
|
|
17
9
|
<br>
|
|
18
10
|
|
|
@@ -24,46 +16,38 @@
|
|
|
24
16
|
|
|
25
17
|
<br>
|
|
26
18
|
|
|
27
|
-
Multi-agent AI development for **Claude Code** and **OpenCode**.
|
|
28
|
-
<br>
|
|
29
|
-
Spawn 24 specialists that self-organize around your goal using pheromone signals.
|
|
30
|
-
|
|
31
|
-
<br>
|
|
32
|
-
|
|
33
19
|
```
|
|
34
20
|
$ npx aether-colony
|
|
35
21
|
```
|
|
36
22
|
|
|
37
23
|
<br>
|
|
38
24
|
|
|
39
|
-
*The whole is greater than the sum of its ants.*
|
|
40
|
-
|
|
41
|
-
<br>
|
|
25
|
+
*The whole is greater than the sum of its ants.* 🐜
|
|
42
26
|
|
|
43
27
|
</div>
|
|
44
28
|
|
|
45
29
|
---
|
|
46
30
|
|
|
47
|
-
##
|
|
31
|
+
## Why Aether
|
|
32
|
+
|
|
33
|
+
Every AI coding tool now has "agents." Most of them are the same thing repackaged — a loop that plans, executes, and checks. That's not a colony. That's one ant doing laps.
|
|
48
34
|
|
|
49
|
-
|
|
35
|
+
Aether is different because it's modeled on how **real ant colonies work**: no central brain, no single agent trying to be everything. Instead, 24 specialized workers self-organize around your goal. A Builder writes code. When it hits something unfamiliar, it doesn't guess — it spawns a Scout to research. When code lands, a Watcher spawns to verify. A Tracker hunts bugs. An Archaeologist digs through git history. They work in parallel, in waves, across phases.
|
|
50
36
|
|
|
51
|
-
|
|
37
|
+
**What actually makes this different:**
|
|
52
38
|
|
|
53
|
-
|
|
39
|
+
🐜 **Pheromone signals, not prompt engineering.** You steer the colony the way a queen steers ants — with signals, not instructions. Drop a FOCUS signal on "security" and every worker weighs it. Drop a REDIRECT on "no raw SQL" and it becomes a hard constraint. The colony adapts without you rewriting prompts.
|
|
54
40
|
|
|
55
|
-
|
|
41
|
+
🐜 **Memory that compounds.** Learnings from one build become instincts for the next. Instincts promote to QUEEN.md wisdom. High-confidence wisdom flows to the Hive Brain and crosses into other projects on your machine. Your colonies get smarter over time.
|
|
56
42
|
|
|
57
|
-
You
|
|
43
|
+
🐜 **Built to be fun.** You set a goal, the colony builds it. You steer with signals, not micromanagement. You watch workers spawn workers. You seal the colony when it's done and start a new one. It feels like tending a garden, not writing tickets.
|
|
58
44
|
|
|
59
45
|
```
|
|
60
|
-
/ant:focus "security" # "Pay attention here"
|
|
61
|
-
/ant:redirect "no jQuery" # "Don't do this"
|
|
62
|
-
/ant:feedback "prefer composition" # "Adjust based on this"
|
|
46
|
+
/ant:focus "security" # 🐜 "Pay attention here"
|
|
47
|
+
/ant:redirect "no jQuery" # 🐜 "Don't do this"
|
|
48
|
+
/ant:feedback "prefer composition" # 🐜 "Adjust based on this"
|
|
63
49
|
```
|
|
64
50
|
|
|
65
|
-
The colony **remembers**. Wisdom, learnings, and instincts persist across sessions. The Hive Brain shares knowledge across colonies on your machine.
|
|
66
|
-
|
|
67
51
|
## Quick Start
|
|
68
52
|
|
|
69
53
|
```bash
|
package/package.json
CHANGED