Zero-dependency AI agent harness for Java 25: agentic loop, tool execution, subagents and SKILL.md support in a singl...
Copy the install, test the workflow, then decide if it earns a permanent slot.
Fresh repo activity plus visible builder pull. This is the kind of tool people test before it turns obvious.
Copy the install, test the workflow, then decide if it earns a permanent slot.
Reasonable to try, but it will take more than a quick skim to get real signal.
GitHub health unknown. no security policy. Fresh enough repo health and manageable issue load keep the risk controlled.
AI Agent
Universal
Model
Multiple
Fastest way to find out if zsmith belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/AdamBien/zsmith ~/.claude/agents/zsmithRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/agents/zsmithNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ skills/ ├─ agents/ │ └─ zsmith/ ← installs here └─ settings.json
Zero-dependency AI agent harness for Java 25: agentic loop, tool execution, subagents and SKILL.md support in a single ~300 KB jar, using only the JDK. Works with Anthropic, Amazon Bedrock, OpenAI-compatible endpoints (Ollama, LM Studio, llama.cpp, vLLM) and on-device GGUF inference via LightMetal.
Source: GitHub repository
Source check: October 16, 2026
Upstream commit: October 16, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.