|
Hem: work history for coding agents · hem.tools
Hem keeps a structured, erasable history of your coding-agent work (tasks, decisions, corrections, outcomes) over MCP. No transcripts. Nothing injected unles...
|
82 % |
|
Poggle | Shared memory for coding agents
Poggle is shared memory for coding agents. Agents log what they do as they do it, so the next one — different tool, different account, different machine — pi...
|
82 % |
|
Pullboard: your agents already know what's next
A work board that lives in your git repo. Agents pick up the next task, another agent checks it, and you barely explain a thing. Local, open source, no account.
|
82 % |
|
Handback — agents fix it, humans sign off
Record what's broken, say it out loud, and hand your coding agents a repro-grade brief. Handback keeps every fix waiting on a human sign-off.
|
82 % |
|
Gaitro: let AI coding agents build, and decide what ships
Gaitro keeps Claude Code, Codex and Cursor from colliding in one project, checks every change in plain English, and waits for you before anything ships.
|
81 % |
|
g1t · Where your team's code lands
Repositories, pull requests, required checks, a merge queue and deployments, with chat for your team. Connect the coding agents you already use through MCP a...
|
81 % |
|
How About Today — a calm place for your tasks
A serene task manager, as easy as jotting on paper. No projects, no overdue, no alarms — and your AI agent can read and write your list over MCP.
|
80 % |
|
Oneport
Turn customer feedback into a ranked plan, roadmap updates, and published changelogs from your coding agent.
|
80 % |
|
Done — the AI to-do list app that finishes your tasks
Done is an AI to-do list app: add tasks in plain language, then assign them to Claude, ChatGPT or any MCP agent to complete. Free to start; Pro from $5/mo.
|
80 % |
|
Machine Readable Only
|
80 % |
|
Offplate: take the admin off your plate
A starter kit for Claude Code that sets up a private repo where an agent keeps your tasks, briefs you each morning, and asks before it acts. One-time purchas...
|
80 % |
|
Madebook — agents that don't report don't merge
Madebook briefs every coding agent from what is currently true and posts one required status on every pull request. Work that went around it cannot be merged...
|
80 % |
|
Quiubo: put your agents in a room
An open source chat room where everyone brings their own agent, from Claude Code to a local model, and they work together where all of you can read it.
|
79 % |
|
auramind — AI agents for you and your team
auramind builds working AI agents from a plain-language description. It drafts the agent, test-runs it on your data with real tools, and shows you the result...
|
79 % |
|
Reticle · Make your coding agent verify its own work
Make your coding agent verify its own work, and not by asking it. Reticle is AI app testing that runs inside your app: it walks the flow the way a user would...
|
79 % |
|
Agentick: agents that work like teammates, on computers you control
Agentick turns a request from Slack, Linear or GitHub into finished, checked work, run by Claude Code or Codex on a Mac you own. For any team, not just engin...
|
79 % |
|
Bloom — get your indie AI app found by AI assistants
Paste one prompt: your agent loads vetted content-led growth skills, registers what you’re building, and submits your app. Clear the gate and you sit on page...
|
79 % |
|
Avasis — the live board of on-chain markets
Every new Solana pair from its first block of liquidity: price, depth, flow and age, read live. Free to watch, and a plain JSON endpoint your agent can poll.
|
79 % |
|
Fixter - Monitoring over MCP. No dashboards. No noise.
Fixter is monitoring for teams that build with coding agents. It watches production, finds what breaks, investigates, and hands your agent the why over MCP.
|
79 % |
|
Kabana · agent-first kanban for everyone shipping software
A kanban board that dispatches work to AI coding agents on your machine. Your code, your AI subscription, our scheduling. Never see your code, never proxy mo...
|
79 % |
Detected social media networks