by jayminwest · Agent Tool · ★ 316
Mulch Structured expertise management for AI agent workflows. Agents start every session from zero. The pattern your agent discovered yesterday is forgotten today. Mulch fixes this: agents call to write learnings, and to read them. Expertise compounds across sessions, domains, and teammates. Mulch is a passive layer. It does not contain an LLM. Agents use Mulch — Mulch does not use agents.
| Stars | 316 |
| Forks | 39 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 75.1416964827792/100 |
| Open Issues | 5 |
| Last Updated | 2026-06-30 |
| Created | 2026-02-10 |
| Platforms | claude-code, node |
| Est. Tokens | ~21k |
These tools work well together with mulch for enhanced workflows:
Explore other popular agent tool tools:
mulch is Growing Expertise for Coding Agents — structured expertise files that accumulate over time, live in git, work with any agent. It is categorized as a Agent Tool with 316 GitHub stars.
mulch is primarily written in TypeScript. It covers topics such as ai-memory, ai-tools, claude-code.
You can find installation instructions and usage details in the mulch GitHub repository at github.com/jayminwest/mulch. The project has 316 stars and 39 forks, indicating an active community.
mulch is released under the MIT license, making it free to use and modify according to the license terms.