v0.4 · Generation 1 · 61 real collapses

A better .cursorrules

Field Activation for AI — make your AI's style measurable, repeatable, exportable.

Give Cursor, Claude, or any LLM a weighted concentration-field layer. Your AI output becomes consistent, precise, and self-improving. 10× what .cursorrules can do.

Live Data

Refreshed on every deploy · all real · never fabricated

AETHER
1
Generation
58
real collapses
1
active species
1
seeds ripening
9
active fields
13
CLI tools
0
⭐ GitHub Stars
0
🍴 Forks
0
📦 Releases
latest
Updated:

Three things .cursorrules can't do

Everything .cursorrules does is a subset of what Aether does

01

Weighted activation

Floating-point dials, not on/off switches

Every field takes a number in [-1, 1]. `linus=0.9` is intense, `linus=0.3` is a whisper. Re-tune in one line without rewriting anything.

.cursorrules: one hardcoded rulebook. Aether: tunable knobs.
activate linus=0.9, ive=0.3
02

Negative concentration

Repel, not just attract

Want the AI to stop sounding like LinkedIn? `linkedin=-0.8` pushes the distribution the other way. Rule systems can't express this — rules only say "do X", never "actively un-do X".

.cursorrules: no way to say "less of this". Aether: negative weights.
activate ive=0.8, linkedin=-0.8
03

Fingerprint quantification

Math distance proves the field actually fired

Did the field shift the output, or did you imagine it? Run `fingerprint.py` on the response — get a number. Palette + keywords + structure, all measured.

.cursorrules: unmeasurable. Aether: every activation leaves a signature.
python tools/fingerprint.py

Same AI · different answer

Same Claude. Same Cursor. Only difference: `activate linus=0.9`.

❌ Without Aether
Here are some suggestions: consider Promise.all for performance, use parameterized queries for safety, add error handling for robustness. Overall the code works but has room for improvement.

SQL injection listed equal to adding a suggestion. Zero severity tiering. "Code works" is wrong — it's dangerous.

✓ linus=0.9 · rigor=0.9
Three bugs, one catastrophic. Catastrophic — line 3 is SQL injection. Database-obliterating. Fix now. Everything else is noise.

Severity-tiered · no hedge words · action-priority closer.

From early users

Aether is young — these are real reactions from its first week alive

Three AI analysts independently reviewed Aether. Objective data: 0% palette overlap across 3 field activations, 75.2% fingerprint keyword hit rate. Field mechanics genuinely shift LLM distribution.

@field-efficacy-test-001
Three-session blind test · 2026-04-17

The system found a bug in its own design (linus and ive fields shared 4 dimensions) and auto-wrote ep-0001 prescription. First time I've seen AI infrastructure self-repair.

@aether-critic-v2
First critic run · coll-0055

From "usable" to "alive" in 8 hours: first real species `engineering-rigor-linus-torvalds` promoted from nursery, Generation jumped 0 → 1. Actual code-layer self-evolution happened.

@orchestrator-v1
Gen 1 launch witness · coll-0057

How Aether compares

Not "a better prompt tool" — a **paradigm shift**

Feature.cursorrulesCLAUDE.mdLangSmithAether
Weighted multi-dim
Negative repel
Fingerprint eval⚠️ quality✅ style
Self-critique
Self-evolution
Zero-dep deploy

Why not just .cursorrules?

Traditional rule systems hit four ceilings. Field mechanics break all four.

01

Can't compose

"Concise AND thorough" — models pick one. Fields are orthogonal dimensions that stack.

02

Can't reverse

"Don't sound like LinkedIn" won't fit in a rule. `linkedin=-0.9` does.

03

Can't measure

Did the model follow your rules? Nobody knows. Fingerprint makes every shift measurable.

04

Can't evolve

Rules need manual edits. Aether writes its own prescriptions, you just review.

4 steps to make it yours

Zero dependencies. Python stdlib only. Install once, use everywhere.

01 Install
git clone https://github.com/497810wsl/aether-kit ~/aether
02 Wire into your project
cd your-project
~/aether/bin/aether init
03 Activate a field in Cursor
activate linus-torvalds=0.9, engineering-rigor=0.8
04 Use a preset · skip the parameters
cat ~/aether/presets/code-reviewer.preset  # 5 presets ready to paste

30 seconds from now, your AI is different.

Zero dependencies · MIT license · works with Cursor / Claude / any LLM