Back to directory

10xProductivity — Personal AI Assistant for Work, Built on Coding Agents

A local-first stack that turns a coding agent such as Cursor, Claude Code or Codex into a personal AI assistant for office work, using the browser sessions, desktop apps and tool access a person already has, with no new company platform to approve.

10xProductivity — Personal AI Assistant for Work, Built on Coding Agents

The project is built around access an employee already has: their coding agent, browser and desktop apps, authenticated sessions, local machine, existing permissions, and notifications, messages and calendar events, rather than a new automation platform, a Slack app, webhooks or an IT project. Pre-built recipes cover more than 25 tools, plus a playbook for connecting any internal or custom tool.

Enterprise search works across connected tools such as Slack, Confluence, Jira, GitHub, Linear and Notion. Packaged Cursor and Claude Code skills handle tool setup, search and workflow creation. A person delegates work in natural language, the agent searches, drafts, triages, updates and automates using connected tools, and the person supervises and corrects it; repeated patterns become reusable skills and working sessions become persistent memory.

Triggers, reusable event listeners that detect a condition and act, are described as an early-stage, upcoming layer on top of the tool connections and enterprise search that are available today.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.