|
Maple: the frontend review toolkit
Maple is the open-source frontend review toolkit. Point at what is wrong on a preview, your agent reads it over MCP, and CI holds the merge.
|
85 % |
|
Hivemind — Run agents in parallel. Break nothing.
Hivemind runs coding agents side by side, keeps each one in its lane, and stops bad changes before they hit your branch.
|
84 % |
|
The Verification Playbook — make your coding agent prove its work
A field manual and working toolkit for engineers who run AI coding agents on real codebases: turn “the agent said done” into changes you can actually trust.
|
84 % |
|
Emberthread — field manuals and tools for persistent coding agents
seamcheck finds code your tests reach that production never calls. The book explains why persistent agents stall, and how to run one that compounds.
|
84 % |
|
superdev — a backlog your AI coding agents can't cheat
The backlog and authority layer for teams running fleets of Claude Code agents against a shared codebase — a Postgres system of record with real row-level se...
|
84 % |
|
Conderis • Reviewed knowledge for coding agents
Shared context for coding agents, with a review step. Decisions, tasks and project instructions reach every agent only after a maintainer approves them.
|
83 % |
|
Ziek | API & SDK Migration Automation
Ziek connects upstream SDK changes to the downstream codebases they affect, identifies where migrations are needed, and prepares test-verified fixes for review.
|
83 % |
|
Typestate — coming soon
Agents forget between sessions. Loops are hand-written. Guardrails are suggestions. A tour of the problems Typestate is built against — and a first look at w...
|
83 % |
|
Agent Ops Kit: drop-in sub-agents, hooks & commands for agentic coding
Stop rebuilding your agent setup on every repo. 8 sub-agents, 6 hooks, 10 commands, 5 CLAUDE.md templates. Works with Claude Code and other agent CLIs.
|
83 % |
|
blazie
The backend agents run on. Durable memory that records where every fact came from, a graph you did not have to model, and sandboxes to run agent code in.
|
83 % |
|
Engineering intelligence on demand
Engineering intelligence on demand, in the form the work needs it — the rules that bind a change, a guide for building something new, a flow when the job has...
|
83 % |
|
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...
|
83 % |
|
ƒ²
Decades of software craft, brought to bear on agentic development for Apple platforms — moving fast, without losing the thread.
|
82 % |
|
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...
|
82 % |
|
BugLoop, shared bug tracking for developers and their clients
|
82 % |
|
Koinos Studio — Core
Koinos keeps your agent fleet aligned to your decisions — and compounds what you know every time you use it. The layer beneath your AI tools.
|
82 % |
|
LeoTrace: Move at agent speed while burning down the debt
Your agents write faster than any review can keep up with. LeoPrevent fixes what they get wrong in the same turn, before anyone opens a review.
|
82 % |
|
Sankalp Gilda — ML consulting, and the work behind it
I build things and write about them — partly so the work is understandable to someone who wasn't there, partly to become a better writer. Current projects: w...
|
82 % |
|
declr
declr gives your coding agents a shared record of tasks, decisions, ownership and handoffs. They can pick up the work, coordinate with each other and leave a...
|
82 % |
|
Hog · Your coding agent has no idea why.
An MCP server that feeds Claude Code and Codex the real product context (Linear, Slack, notes, incidents) before they write a line, so your agent builds on w...
|
82 % |
Detected social media networks