agentic-in/inferoa
Inference-native Tokenmaxxing Agent Harness for Loop Engineering
View on GitHub →Where this sits in the catalog
Most-wanted open issues
Ranked by 👍 reactions. 47 open issues total, checked 2026-10-14.
| Issue | 👍 | Comments | Opened |
|---|---|---|---|
[GA-M3][research] Define internal real-loop corpus taxonomy and manifest kind:research, area:evaluation-harness, area:self-improve, priority:p1-ga | 0 | 0 | 4 mo |
[GA-M3][evaluation] Implement internal corpus runner kind:evaluation, area:evaluation-harness, area:self-improve, priority:p1-ga | 0 | 0 | 4 mo |
[GA-M3][engineering] Add maker/checker policy for eval tasks kind:engineering, area:loop-control, area:evaluation-harness, priority:p1-ga | 0 | 0 | 4 mo |
[GA-M4][evaluation] Generate final acceptance evidence report from ga-eval artifacts kind:evaluation, area:tokenmaxxing-sr, area:release-ops, priority:p1-ga | 0 | 0 | 4 mo |
[GA-M4][testing] Add GA release gate command kind:testing, area:release-ops, priority:p1-ga | 0 | 0 | 4 mo |
Alternatives in CLI coding agents
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you co…
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens b…
An open-source AI agent that brings the power of Gemini directly into your terminal.