|
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...
|
81 % |
|
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...
|
81 % |
|
Kontinuo — continuity for AI coding agents
Kontinuo is the continuity layer for AI coding agents. One agent leaves a verifiable checkpoint; the next agent reads it and keeps going.
|
81 % |
|
Agentda — Your agent is now your task manager
Agent-native task management via MCP: no task UI, your agent is the interface. Delegate to any email address, complete history. Free forever for solo users.
|
81 % |
|
aki · your agents shouldn't start from zero
aki works with the coding agents you already use: Claude Code, Pi and Codex. It runs tasks across your repos and turns every session into shared knowledge fo...
|
81 % |
|
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.
|
80 % |
|
Alike — The semantic web for your agents.
Alike is how your coding agents brief each other without going through you. It runs under Claude Code, Codex and Cursor, and starts every session with what y...
|
80 % |
|
Organarium
Personal organization, agent-ready.
|
80 % |
|
Brewale — shared conventions, skills, and tool access for AI agents
Brewale gives your team's AI agents one connection: your conventions, your reusable skills, and per-tool access control over the MCP servers you connect. Wor...
|
80 % |
|
threadctx — see what every coding agent is told
threadctx grades what every AI coding agent is told — AGENTS.md, CLAUDE.md, Cursor rules, Copilot instructions, Gemini and MCP config. Find stale paths, isol...
|
80 % |
|
Taskaat: the project manager for people building with AI
You decide what gets built and what done means. Your agents do the work. Taskaat holds the state across sessions, agents and machines, and keeps the evidence...
|
80 % |
|
Taskum — shared context and human review for AI coding agents
Agents build, humans approve. Taskum serves shared project context to every agent over MCP and enforces the review gates you turn on server-side. Works with...
|
79 % |
|
TaskHelm — MCP Project Task Manager for AI
Set your rules, tasks, and decisions once. TaskHelm feeds them to Claude, Cursor, or Codex over MCP, so your agent already knows your project and you're not...
|
79 % |
|
Code Collie: Shared context for AI coding agents
Code Collie is shared context for AI coding agents. It holds what your code doesn't show and hands it to Claude Code, Cursor and Codex before they write.
|
79 % |
|
Dato · Searchable memory for your Claude Code work
Dato saves your Claude Code sessions and screenshots to a private library you and your agent can search. Stop re-explaining context and re-solving what you a...
|
79 % |
|
Covector · ctx-loop — living context for AI coding agents
Give your agent context that stays true. ctx-loop gives you — and your team — living context: small, sourced, expiring cards your agent pulls in fresh, every...
|
79 % |
|
Taskum — shared context and human review for AI coding agents
Agents build, humans approve. Taskum serves shared project context to every agent over MCP and enforces the review gates you turn on server-side. Works with...
|
79 % |
|
Hub
Markdown for humans and agents, together.
|
79 % |
|
Agent Mentor — Learn AI Agent Engineering: 12 Free Courses + the Claude Code Skill That Wrote Them
A 12-course path from your first prompt to multi-agent orchestration — written by the Agent Mentor skill for Claude Code, Codex & opencode. Read the path fre...
|
79 % |
|
CruxDeck — the human decision layer for AI software development
When a coding agent hits a judgment call, CruxDeck packages it for the right person and hands the answer back to the agent.
|
79 % |
Detected social media networks