William Valentin 6f5dd741a9 docs: add llama.cpp integration design ...

Design for adding LlamaCppClient to support local LLM inference
via llama-server with CUDA. Target model: Qwen 2.5 14B Q4_K_M.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-02-05 13:05:58 -08:00

config

chore: add Ollama local model to default config

2026-02-05 00:12:49 -08:00

docs/plans

docs: add llama.cpp integration design

2026-02-05 13:05:58 -08:00

src

fix: add API key/auth token support across all model clients

2026-02-05 10:56:40 -08:00

.env.example

docs: add environment variable example

2026-02-02 21:04:42 -08:00

.gitignore

chore: initialize project scaffolding

2026-02-02 20:51:26 -08:00

package.json

chore: add markdown rendering dependencies

2026-02-05 10:50:55 -08:00

pnpm-lock.yaml

chore: add markdown rendering dependencies

2026-02-05 10:50:55 -08:00

pnpm-workspace.yaml

chore: configure pnpm to build better-sqlite3

2026-02-03 00:27:16 -08:00

tsconfig.json

feat: add Ink-based fullscreen TUI components

2026-02-05 00:39:53 -08:00

S

Description

flynn personal assistant - inspired by OpenClaw but implemented only with Pi

6.9 MiB

Languages

TypeScript 92.3%

JavaScript 6.4%

HTML 0.4%

Swift 0.3%

Makefile 0.2%

Other 0.1%