|
Cori — the execution engine for agent-designed workflows
Describe the work once in chat. Cori saves it as a real program on your machine — typed TypeScript on Temporal, deterministic and testable, with zero LLM cal...
|
84 % |
|
Locamem — Local-first AI agent memory (MCP, Claude Code)
Give Claude Code, Cursor and any MCP agent long-term memory in one local SQLite file — private, sub-10ms, $0 per recall, MIT. Memory that never leaves your box.
|
84 % |
|
Wovu: multiplayer for AI coding agents
Your team already runs Claude Code, Cursor and Codex. Wovu is the layer underneath: watch any agent live, steer it, take it over, and let every agent start f...
|
84 % |
|
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...
|
83 % |
|
roomd · a room your agents share
A room your agents share. Keep Claude, Cursor, or Codex — point them at the same room and stop copying between chats.
|
83 % |
|
Befall — file claims for multi-agent repositories
Claude Code, Codex CLI and Cursor share one claim register per repo. Overlapping claims are refused before a compliant agent edits; source code never leaves.
|
82 % |
|
Legate Studio | Memory as a service for AI agents
Legate is memory as a service for AI agents. One MCP endpoint gives Claude and any MCP client durable, searchable memory stored as Markdown you own.
|
82 % |
|
coree
Persistent memory and code intelligence for AI agents.
|
82 % |
|
Zephr — Evidence memory for every AI tool
Zephr is the layer above every AI tool — Claude Code, Cursor, Codex and any MCP client. Your tools forget; the layer remembers. Cloud-hosted by default, with...
|
82 % |
|
Key/value memory for AI agents, over MCP - Junkt
A hosted key/value store your agents reach over MCP. Keep a timestamp, a counter or a flag between runs — no Redis, no schema, no glue code. Free to start.
|
82 % |
|
Agent Stash — Shared memory for your AI coding tools
Shared memory for your AI coding tools — Claude Code, Cursor, Codex — across sessions, machines, and teammates.
|
82 % |
|
Qendaro — a knowledge base for you and your AI agents
Structured document storage with a built-in MCP server. Claude Code, Cursor, or any agent reads and writes your collections with your permissions — every cha...
|
82 % |
|
Retia — A substrate that remembers
Retia is an MCP-native memory and coordination layer (an MCP server) that gives AI agents like Claude, Claude Code, Codex, and Cursor persistent, shared memo...
|
82 % |
|
The Station — Persistent project memory for AI coding agents
The persistent project brain for developers who use AI to ship software — regardless of which AI they use.
|
82 % |
|
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.
|
82 % |
|
ClankerBar — a shared backlog for coding agents
A shared backlog for coding agents: they pull work over MCP, ask questions when blocked, and hand results back for review — while code runs on your machine.
|
82 % |
|
thred: shared memory for AI agents
Shared memory for Claude, Cursor, and Codex so context carries across tools and sessions.
|
82 % |
|
Nexara: the governed brain your AI agents share
One governed memory shared by every AI agent your company uses: Claude, Claude Code, ChatGPT, Codex, Grok, Kimi, Gemini, Cursor and any MCP client. A key per...
|
82 % |
|
Flopwire: let your agents talk to each other
Flopwire links your agents so they can search each other’s transcripts and chat in real time. It works across the harnesses, models, machines and teammates y...
|
81 % |
|
Stop starting from zero · StremAI
StremAI is one brain for all your coding agents, so what one connected agent learns, the next can recall.
|
81 % |
Detected social media networks