Neal – Codex writes the code, Claude reviews it is a coding AI agent for Use one AI model to generate code and another to review it, enabling automated, high-quality code development. Pricing: not stated on the product page. As of 2026-11-05, KanonAgent records 1 upvotes. First indexed by KanonAgent on 2026-08-04.
Codex writes code, Claude reviews it — a two-agent workflow for AI-powered code generation and validation.
1 upvotes
Tracked by Kanon since Aug 4, 2026
Status basis: npm_downloads_7d gained 139 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
📈 Timelinewhat changed, and when
- Accelerating npm_downloads_7d gained 139 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 5 in the last 3d vs 1 in the 3d before (ratio 5.0x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 16 (<= 40% of the prior window)
- Reactivated npm_downloads_7d did not move for 7d, then gained 4 in the last 3d
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 16 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -9 per 3d from 26 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -169 per 3d from 159 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -176 per 3d from 159 (<= 40% of the prior window)
- Anomaly daily change 186.0 is 3.1 standard deviations from this entity's own prior mean (-20.2±66.2, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 159 in the last 3d vs 3 in the 3d before (ratio 53.0x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -27 per 3d from 158 (<= 40% of the prior window)
- Anomaly daily change 186.0 is 3.1 standard deviations from this entity's own prior mean (-20.2±66.2, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 3 per 3d from 128 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 3 per 3d from 128 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -154 per 3d from 233 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -149 per 3d from 236 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -65 per 3d from 164 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 233 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -65 per 3d from 164 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 236 in the last 3d vs 15 in the 3d before (ratio 15.7x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 164 in the last 3d vs 15 in the 3d before (ratio 10.9x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -114 per 3d from 68 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -114 per 3d from 68 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -15 per 3d from 33 (<= 40% of the prior window)
🔎 Known / Unknown
12 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 3 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | openrouter,claude,codex | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · coding
Job to be doneUse one AI model to generate code and another to review it, enabling automated, high-quality code development.
AutonomyL2 · tool-calling(evidence: "runs each scope with your configured coder and reviewer role…")
Who it is forDevelopment teams looking to improve code quality and efficiency through AI collaboration.
Prerequisitesopen source · self-hostable
Integrationsopenrouter · claude · codex
Traction · why it is risingNo public traction data, but the approach demonstrates an early, replicable multi-agent pipeline.
Why it matters
It pioneers a division of labor between AI models—writing and reviewing—which sets a precedent for structured, collaborative agent workflows.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“runs each scope with your configured coder and reviewer roles”— readme
“You write a plan, and neal's planner/reviewer loop turns it into”— readme
“Run artifacts are recorded under .neal/ so interrupted work can resume”— readme
“Each on the provider and model you choose”— readme
“A plan-driven, multi-agent coding loop.”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Building Neal? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is Neal?
Codex writes code, Claude reviews it — a two-agent workflow for AI-powered code generation and validation.
What does Neal do?
Use one AI model to generate code and another to review it, enabling automated, high-quality code development.
Why does Neal matter?
It pioneers a division of labor between AI models—writing and reviewing—which sets a precedent for structured, collaborative agent workflows.
Is Neal open source?
Yes — Neal is open source.
Can I self-host Neal?
Yes — Neal can be self-hosted.
What does Neal integrate with?
openrouter,claude,codex
How popular is Neal?
As tracked by KanonAgent: 1 upvotes (first indexed 2026-08-04).
What are the best Neal alternatives?
Similar AI agents tracked by KanonAgent: deepseek-harness, gemini-cli, Codédex, LLM Gateway, oh-my-openagent, goose.