Versions:

0.89.0
0.88.0
0.87.0
0.86.0
0.85.0
0.84.1
0.84.0
0.83.0
0.82.6
0.81.2
0.80.0
0.78.0
0.77.0
0.76.1
0.76.0
0.75.0
0.74.6
0.74.2
0.74.1
0.73.1
0.73.0
0.72.0
0.71.0
0.70.0
0.68.0
0.67.0
0.66.0
0.65.0
0.62.0
0.61.0
0.60.1
0.60.0
0.59.0
0.58.0
0.57.0
0.56.0
0.55.0
0.52.0
0.51.0
0.50.1
0.44.0
0.43.0
0.41.0
0.40.0
0.37.3
0.37.2
0.37.1
0.37.0
0.36.2
0.36.1
0.32.1
0.32.0
0.31.0
0.30.0
0.21.0
0.19.5
0.19.3
0.19.2
0.19.0
0.18.8
0.18.6
0.18.5
0.18.4
0.18.3
0.18.2
0.18.0
0.17.0
0.16.2
0.16.1
0.16.0
0.15.9
0.15.8
0.15.7
0.15.6
0.15.5
0.15.4
0.15.3
0.15.2
0.15.1
0.15.0
0.14.0
0.13.9
0.13.8
0.13.7
0.13.6
0.13.5
0.13.4
0.13.3
0.13.2
0.13.1
0.13.0
0.12.9
0.12.8
0.12.6
0.12.5
0.12.4
0.12.3
0.12.2
0.12.1
0.12.0
0.11.11
0.11.9
0.11.8
0.11.5
0.11.4
0.11.3
0.11.2
0.11.1
0.11.0
0.10.22
0.10.21
0.10.20
0.10.19
0.10.18
0.10.17
0.10.16
0.10.15
0.10.14
0.10.13
0.10.12
0.10.11
0.10.10
0.10.9
0.10.8
0.10.5
0.10.4
0.10.3
0.10.2

P-ai, published by yokami and currently at version 0.89.0 with 128 recorded versions reflecting its actively evolving development, is a self-growing desktop AI work system designed for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. Falling within the AI assistant and desktop productivity category, it is explicitly positioned not as a chat client but as a complete desktop system organized around conversations, tasks, memory, departments, tools, review, and remote messaging. Its architecture pairs a Rust backend using async concurrency and streaming to guarantee response speed with a Vue 3 and DaisyUI frontend for a clean, customizable interface, while all data is stored locally with no intermediate servers. Typical use cases include delegating work to agents, maintaining long-term and private per-persona memory, reviewing tools, and automating parallel workspace operations. For entry and efficiency, it offers global hotkey summon, voice wakeup, background voice input, and quick screenshots, supporting local sessions, remote sessions, and multiple parallel sessions, with quick commands triggering common operations in a single keystroke. Organization is handled through independently configurable departments and personas, each with its own avatar and private memory, with tasks and sessions separated by department, identity, and responsibility. Local sessions support multi-agent group chat, while remote sessions connect via WeChat, Feishu, DingTalk, OneBot, and other protocols, enabling the assistant to operate across both personal and team messaging environments. Interface and interaction are highly adaptable: UI, chat style, colors, and fonts are all customizable, and multiple windows can run in parallel while remaining fast, clean, and functional. Taken together, P-ai suits users who need a ready-to-use, locally hosted desktop assistant that combines persistent memory, agent delegation, remote messaging integration, and concurrent task automation in one evolving system.

Tags:

agent 145

agentic 74

ai 414

large-language-model 144

llm 217