Agent-Blackbox

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

TaewoooPark/Agent-Blackbox

View on GitHub ↗

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

Agent-Blackbox grew +7.7% in the last 30 days, ranks 754th of 872 in Evaluation & Guardrails, last commit 20 days ago.

Star trajectory

42 days tracked
2026-10-1184 stars today2026-11-22
Momentum

+7.7% in 30d, above the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit 20 days ago, staler than the median of 15d.

How it compares in Evaluation & Guardrails

Agent-Blackbox
84
stars
+7.7% 30d
commit 20 days ago
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 754th of 872 by stars.

Ranked by shared tags, then keywords, then stars
  1. Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and…

    +117 (+85%) in 30d · Committed 9d ago · TypeScript · MIT

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  2. neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by…

    +1 (+1.2%) in 30d · Committed 8d ago · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  3. A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance…

    +98 (+4.8%) in 30d · Committed 12d ago · TypeScript · MIT

    Shares Agent Frontends / Chat UI, Evaluation & Guardrails

  4. 🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every…

    +12 (+3.6%) in 30d · Committed today · TypeScript · MIT

    Shares Agent Frontends / Chat UI, Evaluation & Guardrails

  5. A git hook that won't let you push code you can't explain. Quizzes you on your own diff. Works with Claude…

    Committed 24d ago · Python · BSD-3-Clause

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  6. AI Stupid Level — independent, continuous LLM benchmarks (coding, reasoning, tool use), drift detection and a…

    Committed yesterday · TypeScript · MIT

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  7. Auto researching harness that burns through everything.

    Committed 4d ago · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  8. Laminar - open-source observability platform purpose-built for AI agents. YC S24.

    +87 (+2.5%) in 30d · Committed yesterday · TypeScript · Apache-2.0

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

  9. Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

    +111 (+3.9%) in 30d · Committed 6d ago · HTML · Other license

    Shares Agent Frontends / Chat UI, Evaluation & Guardrails

  10. DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a…

    +8 (+1.8%) in 30d · Committed 5d ago · Go · Apache-2.0

    Shares Evaluation & Guardrails, Agent Frontends / Chat UI

Language
TypeScript
License
MIT License
Contributors
2
Forks
13
Watchers
1
Open issues
0
Releases
119
Created
2026-06-16
Stars this week
+0

You've seen where Agent-Blackbox stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

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

Maintain Agent-Blackbox?

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

Claim this page