Carla v0.1.0: a local llama.cpp loom TUI for growing AI characters
max_paperclips · x · 2026-09-29
Carla v0.1.0 is a new open-source loom TUI and character lab built on llama.cpp that runs fully local. Workflow: base model + seed doc → branching continuations → conversational looms with emergent AI characters. You can run multiple chats at once with /loom [count], and after each turn an evaluator (Jev) checks against a custom behavior spec for looping, spiraling, or harmful language — the grid pulses orange past a threshold. The author calls it a 'video game for crafting digital minds,' inspired by computer-10 and the loom community, and plans to use its eval design for a training phase next.
More from coding & agent
- Manus Founder Red Calls Agents 'People' — But Where's the Line on Delegated Authority? — sujingshen · 2026-09-29
- Running an incident agent on free LLM tiers: quota limits forced a per-operation model routing design — Available_Spare_9161 · 2026-09-29
- Muse vs Grok Bot vs Cue: identity, permissions and payments separate AI agents — sujingshen · 2026-09-29
- 105 real bugs benchmarked: Sonnet 5.5 max scores 55.5, beating GPT-6 Astra at 45 — PawelHuryn · 2026-09-29
- 15 Cloud AI Computers Reviewed: Giving Agents Browsers, Memory and Persistent Environments — sujingshen · 2026-09-29
- Just Give Your Agent yt-dlp Access and It Can Find Any Video Clip — deedydas · 2026-09-29