Item detail
github.com

Yeachan-Heo/gajae-code

Yeachan-Heo/gajae-code is a coding agent harness that RepoRadar is tracking in its Coding Agents section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.9 out of 10.

Score8.4
Popularity1.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity6.6
Open-source/build8.4
Evidence7.2
Workflow potential9.9
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for builders who want a reviewable, evidence-based wrapper around multiple existing coding CLIs without modifying them, especially when persistent goals, replays, and tmux team parallelism are more valuable than yet another single-loop agent.

Who should use it

Developers who want a reviewable harness layered on top of Codex, Claude Code, OpenCode, or Claw CodeTeams running parallel coding work in tmux sessions and looking for a typed leader/team contractBuilders who prefer explicit interview-then-plan-then-execute phases over a single prompt loopAnyone who needs durable goals with completion evidence for audits or handoffs

Who should skip it

Move on from Yeachan-Heo/gajae-code if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

Yeachan-Heo/gajae-code is tracked by RepoRadar as a coding agent harness in the Coding Agents section. It was first seen on 2026-07-02 and last updated on 2026-07-02. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, Yeachan-Heo/gajae-code is strongest on workflow potential (9.9) and open-source/build quality (8.4) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Yeachan-Heo/gajae-code a composite score of 8.4 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

The bundled `computer-use` tool gives the agent native screenshot, mouse, and keyboard control of the host desktop; it is opt-in and gated through settings/tool registration, but reviewers should verify it stays disabled on shared or production workstations; `gjc setup defaults --force` overwrites local workflow skill files; run `gjc setup defaults --check` first and only force-overwrite when you intentionally want the bundled copies to win.

Evidence links
Closest alternatives / related signals
coding-agentharnessclaude-codecodexopencodetmuxmit