Status basis: npm_downloads_7d gained 64 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 64 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 64 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change -178.5 is -3.2 standard deviations from this entity's own prior mean (-59.5±37.7, baseline excludes this point) — unusual, not necessarily adoption
- first observed Kanon started keeping permanent history for this agent
| 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.
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
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.