# knowflow-ai/KnowWork

> Enterprise on-premise AI agent platform built on DeepSeek Harness, adding accounts, department-based permissions, per-session Docker sandboxes, approval of risky actions, audit and token usage tracking.

- Magnitude: 1.0 out of 10 — Steady
- Stars: 49 total · +0 stars measured 2026-10-27, 10:04–11:05 UTC, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-10-21 · Last push: 2026-10-24
- GitHub: https://github.com/knowflow-ai/KnowWork · Page: https://gitnova.dev/en/r/knowflow-ai/KnowWork

## Useful for

- Deploy a private agent service on your own server with install.sh
- Restrict access to models, knowledge bases and tools by department and group
- Set up approval and audit for risky agent tool calls

## Why it’s here

- Star-counter measurements on 2026-10-27 (UTC), 10:04–11:05: 49 → 49 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +2 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 49 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 8
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 7 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v0.0.2 (2026-10-24)

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-21 … 2026-10-27: 0, 16, 13, 5, 7, 6, 0

## Similar by description

1. **shuyu-labs/transwork** — 0.0 · Cooling · AI agents · Shell · Not enough measurements today
   Enterprise desktop AI agent workspace that unifies skills, knowledge bases and digital employees, with private Docker Compose deployment, SSO and access control.
   Full card: https://gitnova.dev/en/r/shuyu-labs/transwork.md
2. **mohakmalviya/frugal-blender-mcp** — 0.0 · Quiet · AI agents · Python · Not enough measurements today
   An MCP server that lets an AI agent build Blender scenes through four tools (discover, execute, inspect, capture) instead of 31, cutting fixed context to 338 tokens with batched, permission-gated edits.
   Full card: https://gitnova.dev/en/r/mohakmalviya/frugal-blender-mcp.md
3. **CopilotKit/OpenBot** — 3.7 · Peaking · AI agents · TypeScript · +46 stars measured 2026-10-27, 00:36–11:08 UTC, ≈ 102 by evening
   A platform for running AI coworkers inside your own infrastructure: each gets a browser, files and tools, with every action going through a gateway for approval and audit. Works with any AG-UI agent.
   Full card: https://gitnova.dev/en/r/CopilotKit/OpenBot.md
4. **Anil-matcha/open-duet** — 2.4 · Steady · AI agents · Python · +9 stars measured 2026-10-27, 00:38–11:08 UTC, ≈ 22 by evening
   Self-hosted workspace for running coding-agent tasks (e.g. Claude Code) in disposable Boat sandboxes via a Telegram bot or a Next.js web UI. Prototype with encrypted credentials, approval prompts for risky actions, and task scheduling.
   Full card: https://gitnova.dev/en/r/Anil-matcha/open-duet.md
5. **QuantumNous/new-api** — 3.4 · Steady · Language models · Go · +47 stars measured 2026-10-27, 00:36–10:53 UTC, ≈ 93 by evening
   Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management.
   Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-27 11:09 UTC, updated every 30 minutes.