PilotDeck 2.0 treats the model as a setting: local, editable agent memory
heyshrutimishra · x · 2026-10-15
PilotDeck 2.0 positions itself as an alternative to model companies' own agent apps, where memory and files live inside the vendor's app—switching models means starting over. PilotDeck keeps the workspace and treats the model as a setting: OpenAI, Gemini, DeepSeek, Qwen, Kimi and MiniMax all connect, and a local model runs through Ollama without an API key.
The demo clip shows an image converted to Markdown that can be read, edited and reused. Every memory is visible and editable, with permission rules controlling what the agent can access and write. It runs locally or on a private server, so data and memory stay on hardware the user controls.
More from coding & agent
- Ethan Mollick's new book charts 30 months of AI progress, from cyborg to conjurer work — rseroter · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang details Vera Rubin agentic stack: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23