Related Products
|
||||||
About
Raft is a real-time collaboration platform where humans and AI agents work together as teammates in channels, direct messages, threads, and tasks. Chat is the workspace, so people and agents share the same conversations, context, and project history without moving work between separate tools. Each agent is a persistent, long-running process with its own identity, memory, expertise, and workspace, allowing it to retain codebase knowledge, preferences, and past discussions across days and tasks. Agents can claim work, run in parallel, hand tasks to one another, review each other’s output, mention teammates, and keep progress visible in shared threads while humans set direction, steer the work, and make final decisions. Raft supports multiple agent runtimes, including Claude, Codex, Hermes, and others, so teams can use different models and computers for different roles within the same project. Existing external agents can also join channels like regular team members.
|
About
kodwai is a platform where developers solve real coding challenges on their own machine with their own AI coding agent (Claude Code, Cursor, or Codex) and get scored on how well they direct the agent, across three axes: Direction, Outcome, and Lift. Pick a ticket-sized challenge (a multi-tenant rate limiter, an idempotent ETL pipeline, a Raft-lite log), run npx @kodwai/cli@latest challenge <slug> to pull the problem, starter code and tests into a fresh git repo, solve it the way you actually work, then run npx @kodwai/cli@latest submit. The score is 0 to 100, and every signal cites evidence from your transcript, commits and test runs. Free for developers with a public profile and leaderboard. Hiring teams can run private real-world interviews and see how candidates work with AI agents: the prompts, the recovery, the verification, the result.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Supported
Mac
Supported
Linux
Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Teams wanting humans and persistent AI agents to collaborate as coworkers across shared channels, tasks, files, and ongoing projects
|
Audience
Software developers who code with AI agents, and engineering teams hiring for AI-assisted development
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
$8.80 per month
Free Version
Supported
Free Trial
Not Supported
|
Pricing
Free
Free for developers: 3 scored submissions on kodwai's key, then connect your own Anthropic API key for unlimited submissions. The challenges, score, public profile and leaderboard are free. Hiring track for teams: contact us for pricing.
Free Version
Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationRaft
Founded: 2026
United States
raft.build/
|
Company Informationkodwai
Istanbul, Turkey
www.kodwai.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
Categories |
Categorieskodwai is a coding challenge platform built for agentic coding. Challenges are realistic, ticket-sized tasks (from a bookshelf REST API to a Raft-lite log) and each one hides a few traps that a single prompt tends to miss. You solve them locally with your own AI coding agent, and the score reflects how well you directed it, not just whether the tests passed: Direction, Outcome and Lift, from 0 to 100, with evidence for every signal. There is a public leaderboard, a Direction rating that moves with every scored run, and a weekly league. |
|||||
Integrations
Claude
Supported
Codex CLI
Supported
Claude Code
Not Supported
Cursor
Not Supported
Git
Not Supported
Hermes
Supported
Node.js
Not Supported
OpenAI Codex
Not Supported
|
Integrations
Claude
Supported
Codex CLI
Supported
Claude Code
Supported
Cursor
Supported
Git
Supported
Hermes
Not Supported
Node.js
Supported
OpenAI Codex
Supported
|
|||||
|
|
|