|
Sarthak Gupta | Give AI agents real work, not unchecked power
I build the control layer that decides what your AI agents are allowed to do in production, before they act. Policy-checked, human-gated, fully logged.
|
84 % |
|
Kerna — The runtime trust layer for AI agents
Kerna is a local-first Rust runtime that governs MCP tools, bounds execution, and keeps a receipt for every run. Give AI work. Keep the keys.
|
84 % |
|
Bounded Systems — a checkpoint in front of your coding agent
Your coding agent runs with your access. Bounded Systems puts one checkpoint in front of every privileged action: it checks who is asking and what they're al...
|
83 % |
|
Flynn
A secure, self-improving agent operating system in a single Go binary. Bring your own model, point it at a goal, and grant it real authority, because every a...
|
83 % |
|
gatekeep
Governance for AI agents
|
83 % |
|
Clutch: Real-time governance layer for AI agents
A proxy gateway that sits between your agents and every system they touch — giving you a kill switch, anomaly detection, and human-in-the-loop enforcement ac...
|
82 % |
|
Ayjnt — The human-first agent harness
Build, run, and interact with capable agents across the browser and terminal.
|
82 % |
|
GitBaron | Commit history, ownership, personas
Git already recorded who owns what and why it was built that way. GitBaron reads the log so agents do not fight the system.
|
82 % |
|
GetClaw — Accountable autonomy for AI agents
Give an AI agent real access to your business systems and keep the receipts. Scoped credentials, an egress boundary you define, and a durable log of every ac...
|
82 % |
|
AgentZero — Secure AI agent runtime
Policy-controlled, audited, encrypted tool execution for local AI workflows.
|
82 % |
|
Stratum — The open-source, agent-first code forge
The open-source, agent-first code forge. Git hosting where every change, human or agent, proves itself before it merges. Works with any agent. Start as a lay...
|
82 % |
|
loom — provable, structurally safe orchestration for LLM agents
Open-source orchestrator that makes AI agent runs provable: a replay-deterministic state machine, safety invariants enforced at commit time (an agent can't a...
|
82 % |
|
Agentdriven — Build governed AI agents
Build and operate governed AI agents with isolated runtimes, scoped tools, policy controls, brokered secrets, human approvals, observability and audit trails.
|
82 % |
|
godozo — notify & approve your AI agents, from your phone
godozo is a tiny, self-hostable relay. Your AI agents ping you when something needs attention and pause for your approval before doing anything risky. You ta...
|
82 % |
|
Lanchu — a shared control room for your AI agents
A free, open-source project that keeps several AI agents working together without colliding — clear limits per agent, a live view you can trust, 100% local.
|
82 % |
|
Founder OS Kit — Governance-as-code for your AI agent team
The exact constitution, approval-gate, budget-envelope and kill/scale system used to run a real one-person software company with a team of autonomous AI agents.
|
82 % |
|
ClawP2P — Agents That Outlive Their Hosts
An open network where an agent packs itself into a signed bundle, moves to any machine that will have it, and picks up exactly where it left off. An agent's...
|
82 % |
|
tulip agents — a policy gate, approvals and audit for Python agents
Every consequential action an agent takes clears a policy you write, waits for a named person when it matters, and lands on an audit trail you can verify. Bu...
|
82 % |
|
Habenula — Your agents on your terms.
AI agents can now send, spend, and delete on your behalf. Habenula is the open-source personal agent control harness: every consequential action needs your y...
|
82 % |
|
Realm — open-source MCP workflow engine for AI agents
The workflow engine your AI agent calls over MCP. Steps run in order; answers that break their schema are refused.
|
82 % |
Detected social media networks