artale
/
fable-agent
Template
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

harness-agnostic, model-agnostic: the core thesis

This commit is contained in:
artale 2026-06-13 10:53:47 +02:00
parent ee59a98c7e
commit ac9a8ca32b
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -1,15 +1,15 @@
# Fable Agent
**Self-improving agent system — loops, dynamic workflows, routines.**
**Harness-agnostic, model-agnostic, self-improving agent system — loops, dynamic workflows, routines.**
Stop prompting. Start building a system that compounds.
The harness, not the model. Swap any executor, any model, any provider — the system compounds regardless.
```
node dist/index.js demo
# 3 seconds. Research → Learn → Sharpen → Compound. Live data.
```
Every run leaves the next run smarter. Every state file accumulates. Every skill sharpens. Model-agnostic — works with Sonnet 4.6, GPT-4.1, local models, Pi, or any LLM backend.
Every run leaves the next run smarter. Every state file accumulates. Every skill sharpens.
```bash
git clone https://github.com/movez/fable-agent

2
src/index.ts
View File

@ -18,7 +18,7 @@ const program = new Command();
program
.name("fable-agent")
.description("Self-improving agent system — loops, dynamic workflows, routines")
.description("Harness-agnostic, model-agnostic self-improving agent system — loops, dynamic workflows, routines")
.version(packageJson.version);
// ── Run ─────────────────────────────────────────────────────