|
Agent Curfew — Do you know where your agent is?
Agent Curfew continuously records your agents' movements — without asking the agent to report itself. See what each agent touched, which tools it used, where...
|
85 % |
|
devrandom • Accountable AI Agents
Open-source infrastructure for AI agents you actually control: every agent gets an ID you issue, every action leaves a tamper-proof record, and you can cut i...
|
84 % |
|
SafeClaw: give your agent API access, not API keys
Let your agent work freely: it holds a phantom key, your machine swaps in the real key at egress, and one passkey tap guards anything sensitive.
|
84 % |
|
Agents CLI — the missing toolchain for CLI coding agents
Run Claude Code, Codex, and Gemini together — version-pinned per project. Sessions, secrets, parallel teams, browser automation. One install.
|
84 % |
|
Runvault — the secure agent shell
An agent with a real Linux shell — and the secrets locked out. Credentials stay behind a server-side proxy the sandbox never sees, and every action is logged.
|
84 % |
|
K3 - Agent Runtime for Developers
Run Claude Code, Codex, and any supported agent in isolated workspaces with a full record of everything they did. Native desktop app for macOS, Windows, and...
|
83 % |
|
Donkit — turn what you know into an AI agent people pay to use
Describe what your audience needs and Donkit builds the AI agent, with its own app, sign-in and payments. Set your price and get paid every time it’s used.
|
83 % |
|
Realm — One workspace for every coding agent, on your Mac.
Realm gives every coding agent a space on your Mac: split panes for sessions, terminals, browsers and documents, a shared context pool, and one MCP gateway t...
|
83 % |
|
dough — build and run your own agents on isolated compute
Build and run your own agents — and apps — on isolated compute you control. The key never touches the box.
|
83 % |
|
agent-env — Universal secret injection for AI coding agents
One command. Every agent. Secrets stay out of your shell history. Works with Claude Code, Codex, Aider, Goose, and any CLI agent.
|
83 % |
|
Meshly Build · AI Agent Operations Platform
The control plane for AI coding agents. Kanban for humans and agents, working side by side. Plan, delegate, review, audit. One workspace, ready for enterprise.
|
83 % |
|
Clome
A local-first desktop workspace. Notes, mail, terminals, knowledge graphs, and agents.
|
83 % |
|
silicon38 — a dynamic multi-agent organization
|
83 % |
|
Valmis — Open-source AI agents built for work
Open-source, self-hosted AI agents that do real work without ever holding your API keys — sandboxed, proxied, with 100+ integrations and any LLM you like.
|
83 % |
|
Cipherlatch — Agentic Access Management
Cipherlatch gives every AI agent scoped, revocable, short-lived access — the latch opens only for a verified request, and the keys stay in your custody.
|
83 % |
|
Millwright — The agent builds the machine
|
83 % |
|
Blastpen — somewhere for the agent to be wrong
An OS-isolated sandbox runtime for coding agents. Any CLI agent, a git worktree of its own, confined by the operating system.
|
83 % |
|
Redshift Hub: run AI agents in parallel across git worktrees
Run a fleet of Claude Code agents in parallel, each in its own git worktree, from one native macOS app. Visual git client, PR review and merges built in. Fre...
|
82 % |
|
ctx Consulting · Autonomous AI agents with no security gaps
ctx Consulting embeds autonomous AI agents into your operations inside an isolated architecture: credentials held outside the agent, every outbound call chec...
|
82 % |
|
Retasc: the issue tracker that hands your backlog to AI agents
The issue tracker for AI coding agents. Run your whole fleet in parallel on one backlog, with no collisions and no stranded work.
|
82 % |
Detected social media networks