Open-source agent uses Gemini 3 Flash to autonomously write novels with streaming output and context compression
tom_doerr · x · 2026-08-13
Developer Doriandarko released gemini-writer, an open-source autonomous writing agent powered by Google's Gemini 3 Flash model. It can independently plan and execute creative writing tasks such as novels and short story collections.
Key features include:
- Autonomous planning and execution of writing tasks
- Support for multiple formats (novels, books, short story collections)
- Real-time streaming output showing the agent's thinking and writing
- Smart context management with automatic compression near token limits
- Recovery mode to resume interrupted work from saved context summaries
- Real-time token monitoring with automatic optimization
- Tool use: can create projects, write files, and manage its workspace
- Uses Gemini's thinking mode for better reasoning
The project is open-sourced on GitHub with 313 stars and 55 forks.
More from coding & agent
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16