
The AI coding agent for building ambitious software
The AI coding agent for building ambitious software
Agent AFK records 0 monthly visits with 0% month-over-month growth and Free pricing. jcode records 18,136 monthly visits with -22.7% growth and Freemium, Contact for Pricing pricing.

Open-source coding agent that verifies its own work and pings you when done
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | agentafk.com | jcode.sh |
| Pricing Model | Free | Freemium, Contact for Pricing |
| Monthly Visits | 0 (0) | 18.14K (18,136) |
| MoM Traffic Delta | 0 (0%) | -5.33K (-22.7%) |
| Primary Market & Share | 🌐 Global (—) | 🇺🇸 United States (66.1%) |
| Direct Visits / mo | 0 | 11.87K |
| User Rating | 4.6 | 4.2 |
| Supported Platforms | Website | Website |

Open-source coding agent that verifies its own work and pings you when done
A second adversarial agent re-derives subagent claims before they reach your diff, so 'finished' has to prove it is correct rather than just assert it.
Interact in the CLI REPL, let the background daemon run unattended jobs, or follow and control a session from Telegram with /watch and /abort.
The in-session agent acts as an orchestrator that fans work out to parallel subagents, gathers results, and re-checks before merging.
Commands such as /review, /mint, /diagnose, /shadow-verify, and /ship fan out parallel reviewers or build pipelines instead of sending a single prompt.

Open-source Rust coding agents for your terminal, built for parallelism
Each additional jcode session costs megabytes rather than hundreds of megabytes, and a new session is ready for input in well under a tenth of a second, so you can run many agents on hardware you already own.
Launch multiple agents in parallel, hand off long jobs to background or headless execution, and keep durable task state so work survives interruption.
The jcode bench suite (float-print, json-unescape, utf16-transcode) scores optimization depth on an analog axis with no capping timeouts, so capability differences stay visible.
Agents rate confidence when a task item is assigned and again when it is finished; a sudden jump triggers forced re-verification instead of blind acceptance.

The AI coding agent for building ambitious software
The AI coding agent for building ambitious software
Google's agent-first development platform for building and shipping software with AI agents
Google's agent-first development platform for building and shipping software with AI agents
Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.
Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.
SpecialistA spec-driven AI IDE and agent platform that plans, builds, reviews, and verifies real engineering work.
SpecialistA spec-driven AI IDE and agent platform that plans, builds, reviews, and verifies real engineering work.
Cognition's autonomous software engineer that ships real pull requests

The coding agent that learns your coding taste
The coding agent that learns your coding taste
Free / Open-sourceA minimal, extensible terminal coding agent you can reshape
Free / Open-sourceA minimal, extensible terminal coding agent you can reshape
Free / Open-sourceRun many coding agents in parallel, each in its own worktree
Free / Open-sourceRun many coding agents in parallel, each in its own worktree
SpecialistAn AI IDE and coding agent that works on your project, not just your cursor
SpecialistAn AI IDE and coding agent that works on your project, not just your cursor

AI-powered terminal and agentic software factory for development teams

Agent orchestration platform for your whole software development lifecycle
Agent orchestration platform for your whole software development lifecycle
Free / Open-sourceOpen-source coding agent built for low-cost, open-weight language models
Free / Open-sourceOpen-source coding agent built for low-cost, open-weight language models