# amiya-special/Dynaflow

> Research codebase for learning free-form multi-agent orchestration, letting a main model either answer directly or build and run agent workflows with subagents and tools. Supports direct, dynamic and forced modes via an OpenAI-compatible API.

- Magnitude: 5.1 out of 10 — Early signal
- Stars: 113 total · +2 stars measured 2026-10-28, 05:41–07:47 UTC, ≈ 50 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-10-22 · Last push: 2026-10-27
- GitHub: https://github.com/amiya-special/Dynaflow · Homepage: https://arxiv.org/abs/2610.34467 · Page: https://gitnova.dev/en/r/amiya-special/Dynaflow

## Useful for

- Run the demo in dynamic mode to compare direct answers with model-generated workflows.
- Evaluate token usage and answers across direct, dynamic and forced modes on your own questions.
- Build a Docker-based workflow runtime to execute tool calls from generated agent workflows.

## Why it’s here

- Star-counter measurements on 2026-10-28 (UTC), 05:41–07:47: 111 → 113 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +50 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 113 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #198.
- About 19 forks a day — people are taking the code.

## 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: 13
- Issues and pull requests: 2
- Watchers: 10
- Average over the last week: 23 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

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

2026-10-22 … 2026-10-28: 1, 0, 0, 0, 6, 105, 2

## Spotted in now

- Top new repositories this week: #198

## More in this category

1. **HKUDS/DeepTutor** — 9.1 · Breakout · AI agents · Python · +876 stars measured 2026-10-28, 00:01–07:46 UTC, ≈ 2,466 by evening
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **elayadesign/ai-design-skills** — 8.8 · Breakout · AI agents · +829 stars measured 2026-10-28, 00:01–07:46 UTC, ≈ 2,184 by evening
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
3. **unclebob/ub-mode** — 8.3 · Breakout · AI agents · +643 stars measured 2026-10-28, 00:02–07:46 UTC, ≈ 1,906 by evening
   An agent skill that enforces disciplined software engineering practices when writing or changing code: TDD, root-cause fixes, behavior testing, and quality gates via mutation testing. Installed as SKILL.md into the agent's skills directory.
   Full card: https://gitnova.dev/en/r/unclebob/ub-mode.md
4. **nightly-labs/openbot** — 8.3 · Breakout · AI agents · TypeScript · +312 stars measured 2026-10-28, 00:02–07:46 UTC, ≈ 963 by evening
   A local-first desktop workspace for persistent AI teammates: each agent (Codex, Claude, Grok, and others) gets its own workspace, task queues, file sharing, an embedded browser, and agent-to-agent messaging.
   Full card: https://gitnova.dev/en/r/nightly-labs/openbot.md
5. **CopilotKit/OpenDuet** — 7.8 · Early signal · AI agents · TypeScript · +300 stars measured 2026-10-28, 00:02–07:46 UTC, ≈ 815 by evening
   A self-hosted proactive AI agent built on OpenBot and CopilotKit: it starts work on its own, runs in its own browser, and asks for approval before acting.
   Full card: https://gitnova.dev/en/r/CopilotKit/OpenDuet.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 2026-10-28 07:58 UTC, updated every 30 minutes.