zero is a coding AI agent for To automatically generate, refactor, or debug code according to user-defined rules. Pricing: not stated on the product page. As of 2026-10-22, KanonAgent records 72 upvotes. First indexed by KanonAgent on 2026-08-16.
A customizable AI coding assistant that autonomously executes tasks based on user-defined rules, models, and machines, acting as a true programming co-pilot.
72 upvotes
Tracked by Kanon since Aug 16, 2026
Status basis: npm_downloads_7d momentum fell to 19 per 3d from 106 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to 19 per 3d from 106 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 19 per 3d from 106 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 106 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 106 in the last 3d vs 2 in the 3d before (ratio 53.0x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 106 in the last 3d vs 16 in the 3d before (ratio 6.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 16 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -63 per 3d from 20 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -11 per 3d from 36 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -6 per 3d from 73 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -31 per 3d from 74 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 74 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -11 per 3d from 133 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 85 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -48 per 3d from 133 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 84 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 133 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 77 (<= 40% of the prior window)
- Anomaly daily change 38.5 is 3.0 standard deviations from this entity's own prior mean (-21.9±19.9, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 133 in the last 3d vs 77 in the 3d before (ratio 1.7x, threshold 1.5x)
- Anomaly daily change 38.5 is 3.0 standard deviations from this entity's own prior mean (-21.9±19.9, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 77 (<= 40% of the prior window)
- Anomaly daily change 38.5 is 3.0 standard deviations from this entity's own prior mean (-21.9±19.9, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 38.5 is 3.0 standard deviations from this entity's own prior mean (-21.9±19.9, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 38.5 is 3.0 standard deviations from this entity's own prior mean (-21.9±19.9, baseline excludes this point) — unusual, not necessarily adoption
🔎 Known / Unknown
12 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | 1 | inferred | 1 quote(s) |
| Autonomy level | 2 | inferred | 2 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🚀 Breakout logappend-only · timestamped
2026-08-22ProductHuntflagged at 121 upvotes → now ▲130
Full breakout log →🤖 Agent teardown · coding
Job to be doneTo automatically generate, refactor, or debug code according to user-defined rules.
AutonomyL2 · tool-calling(evidence: "edit files, run commands, use browser/terminal helpers…")
Who it is forDevelopers
Prerequisitesopen source · self-hostable · bring your own API key
Integrationsmcp
Traction · why it is rising121 PH votes
Why it matters
Its emphasis on user-defined rules enables true autonomy, moving beyond passive AI responses and positioning it as a potential cornerstone of an agent-driven development ecosystem.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Zero is an AI coding agent for your local terminal.”— readme
“Bring OpenAI, Anthropic, Gemini, Groq, OpenRouter, DeepSeek, Mistral, xAI, Qwen, Kimi, GitHub Models, Ollama, LM Studio, or any OpenAI-/Anthropic-compatible end”— readme
“edit files, run commands, use browser/terminal helpers”— readme
“keep durable local sessions while you choose the model”— readme
“Use MCP servers, skills, plugins, hooks, and specialist subagents”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building zero? 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 zero?
A customizable AI coding assistant that autonomously executes tasks based on user-defined rules, models, and machines, acting as a true programming co-pilot.
What does zero do?
To automatically generate, refactor, or debug code according to user-defined rules.
Why does zero matter?
Its emphasis on user-defined rules enables true autonomy, moving beyond passive AI responses and positioning it as a potential cornerstone of an agent-driven development ecosystem.
Is zero open source?
Yes — zero is open source.
Can I self-host zero?
Yes — zero can be self-hosted.
What does zero integrate with?
mcp
How popular is zero?
As tracked by KanonAgent: 72 upvotes (first indexed 2026-08-16).
When did zero take off?
KanonAgent flagged zero as breaking out on 2026-08-22 on ProductHunt (at 121 upvotes that moment). The breakout log is append-only: https://kanonagent.com/rising
What are the best zero alternatives?
Similar AI agents tracked by KanonAgent: deepseek-harness, gemini-cli, Codédex, LLM Gateway, oh-my-openagent, goose.