dsh-auto-review

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

PerryLink/dsh-auto-review

View on GitHub ↗

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

dsh-auto-review grew +9.0% in the last 30 days, ranks 1504th of 2,795 in Agent SDK / Framework, actively maintained, last commit today.

Star trajectory

82 days tracked
2026-08-31255 stars today2026-11-22
Momentum

+9.0% in 30d, above the Agent SDK / Framework median of +1.4%.

Maintenance

Last commit today, fresher than the median of 15d.

How it compares in Agent SDK / Framework

dsh-auto-review
255
stars
+9.0% 30d
commit today
Agent SDK / Framework median
290
stars
+1.4% 30d
commit ~15d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 1504th of 2,795 by stars.

Ranked by shared tags, then keywords, then stars
  1. Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live…

    +1.5k (+105%) in 30d · Committed today · TypeScript · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Ship to Users

  2. AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation…

    +7 (+0.6%) in 30d · Committed 16d ago · Python · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Ship to Users

  3. Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an…

    +4 (+1.0%) in 30d · Committed 34d ago · TypeScript · MIT

    Shares Agent SDK / Framework, Ship to Users, Evaluation & Guardrails

  4. Stop AI agents from doing things you didn't ask for.

    +2 (+0.5%) in 30d · Committed 42d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework, Ship to Users

  5. Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

    +1 (+0.5%) in 30d · Committed 724d ago · Svelte · GPL-3.0

    Shares Agent SDK / Framework, Evaluation & Guardrails, Ship to Users

  6. Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and…

    +5 (+3.1%) in 30d · Committed today · TypeScript · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails, Ship to Users

  7. Disciplined Agentic Engineering — a methodology kit for Claude Code: acceptance-test-first specs, explicit…

    +5 (+3.1%) in 30d · Committed 10d ago · Python · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework, Ship to Users

  8. 🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input…

    -2 (-1.4%) in 30d · Committed yesterday · TypeScript · Other license

    Shares Agent SDK / Framework, Evaluation & Guardrails, Ship to Users

  9. Operation-bound protection for autonomous AI agents: contain and verify operations before committing changes…

    +0 (+0.0%) in 30d · Committed 75d ago · Rust · Apache-2.0

    Shares Agent SDK / Framework, Ship to Users, Evaluation & Guardrails

  10. Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

    +2.4k (+84%) in 30d · Committed 12d ago · Python · MIT

    Shares Ship to Users, Evaluation & Guardrails, Agent SDK / Framework

Language
TypeScript
License
Apache License 2.0
Contributors
7
Forks
9
Watchers
0
Open issues
1
Releases
49
Created
2026-08-13
Stars this week
+6

You've seen where dsh-auto-review stands today.

Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain dsh-auto-review?

Claim this page to add your own call-to-action.

Claim this page