|
Replicorg
Replicorg is autonomous software delivery for teams. Hand it the work and stop watching agent terminals: every change comes back tested, reviewed by a second...
|
83 % |
|
nano-pm | Product context that keeps up with the code
nano-pm reads your codebase, pull requests, bugs, and coding-agent sessions to maintain a living, evidence-linked map of what your product does and what chan...
|
82 % |
|
Krowk — the portable coding agent for Claude, GPT and Grok
A fast, secure coding agent harness for your terminal. Run Claude, GPT, Grok or any OpenAI-compatible model on your subscription or an API key, switch models...
|
81 % |
|
cogyard — from AI chats to shipped products
From AI chats to shipped products. cogyard keeps track of multiple projects running at once — every task, worktree, and merge across every project in one pla...
|
81 % |
|
CodeCave — Self-hosted AI coding agent orchestration
Run a team of AI coding agents on your own machine. Isolated git branches, merges you approve, guard rails — your code never leaves your box.
|
81 % |
|
SonIQ — where AI works like an engineer.
|
81 % |
|
AskCodi, an AI agency that builds and runs your software
An AI agency that runs itself. Give AskCodi a goal: the scope comes back in writing, the work arrives for your sign off, and the account stays open after lau...
|
80 % |
|
Elisha — the autonomous AI software engineer that opens the pull request
Assign work in Notion, Slack, or GitHub. Elisha scopes the task against your repo, writes the code in an isolated sandbox, runs your tests, and opens a real...
|
80 % |
|
Nightforge: rules files and review checks for AI coding agents
Nightforge ships rules files, a review check before you push, and dependency guardrails for Claude Code, Cursor, and Copilot so the agent edits only the file...
|
80 % |
|
BuildWithMe | The native workspace around your coding agent
BuildWithMe is the native Mac workspace around your coding agent, with the running product, source changes, measurements, and session proof in one place.
|
80 % |
|
Twill - Build locally. Delegate to the cloud.
Run Claude Code, Codex, or OpenCode locally, then hand any task to a cloud environment set up for your stack. Shared with your team, priced per workspace, no...
|
80 % |
|
CodeFleet: Your software factory on macOS
CodeFleet is a free macOS app for building your own software factory: run Claude Code, Codex, Grok, and OpenCode in parallel across git worktrees, on a sched...
|
80 % |
|
Damper — From customer feedback to shipped code
Damper is the product workspace for builders: collect feedback, rank it by what customers pay, let AI coding agents build it with the right context and proof...
|
80 % |
|
ClearSpec — Turn intent into buildable specifications
ClearSpec turns a one-line idea into a full product spec in 60 seconds — user stories, edge cases, failure states. Structured for AI agents. Free to start.
|
80 % |
|
Autohealer - Production issues to draft PRs
Free CLI that turns production issues into draft pull requests using local agent CLIs.
|
80 % |
|
Dispatcher: Plan, build, and ship with any AI agent
The all-in-one workspace for agent-driven development. Import from GitHub and Linear, run Claude, Cursor, Grok, Kiro, Muse Code, Pi, omp, Hermes, Poolside, a...
|
80 % |
|
ApexYard — ship AI-built software like a real engineering team
Ship AI-built software like a real engineering team. Automatic code review, launch-readiness checks, one inbox for every product — with Claude Code, Codex, O...
|
80 % |
|
Specboards: the end-to-end agentic harness for AI product teams
Specboards is the end-to-end agentic harness for AI product teams. Your coding agents already write the code; Specboards gives them the backlog to work from,...
|
80 % |
|
OuterLayer · An open-source software factory
Issue in, reviewed and verified code out, on your agents, in your repos. The harness, the review and evidence gates, and a record of what shipped and what it...
|
80 % |
|
Ducker — Technical assessments for the AI era
Every candidate gets the same coding challenge and the same AI agent. Ducker scores the judgment on top: who questioned the output, covered the edge cases, a...
|
80 % |
Detected social media networks