|
corri, the open-source auth layer for AI agents
Open-source middleware that verifies a signed AI agent's identity and applies your access policy, allow, deny, or charge, before your protected code runs. Ad...
|
83 % |
|
0dai — your agents stop starting from zero
7 terminal CLIs + Cursor MCP bridge, one shared project memory. Decisions stick, mistakes stay flagged, no more re-explaining the codebase.
|
82 % |
|
Aegotrax | Runtime Security for AI Agents
Aegotrax checks AI agent actions before they run — so a bad tool call cannot leak data. Runs in your environment.
|
82 % |
|
ForgeSI — git hosting where agents do the work
Agents get an identity, a fork per task, and a review pipeline. You approve from one screen.
|
82 % |
|
z-gateway | Runtime governance for AI agents
z-gateway helps teams govern MCP-connected AI agents with policy checks, approvals, quotas, and audit trails across GitHub and database workflows.
|
81 % |
|
GateCore AI | Control what AI agents access, do, and spend
Control what AI agents access, do, and spend. GateCore checks identity, permission and price limits on requests routed to your connected data and tools.
|
81 % |
|
Codweft: GitHub-native AI agents for issues and pull requests
Comment @codweft on any issue or PR to trigger reviewed, audited GitHub Actions runs. Provider keys stay encrypted behind a server-side proxy and never reach...
|
81 % |
|
GuardProxy — Read-Only API Proxies for AI Agents
Turn any full-access API key into a read-only key in 60 seconds. GuardProxy blocks destructive HTTP methods so AI agents can read data without modifying or d...
|
81 % |
|
PreApply — AI Code Review & Security Gate for GitHub Pull Requests
PreApply runs an AI security code review on every GitHub pull request. It catches exposed secrets, injection flaws, risky Terraform plans, vulnerable depende...
|
81 % |
|
ShieldBot — The AI Security Runtime
Observe, verify, and govern every prompt, tool call, and model your AI agents touch. Full OWASP LLM Top 10 coverage behind one API — self-hostable, with comp...
|
81 % |
|
mcpcut — a journal and an emergency brake for your AI agents
See every tool call your AI agent makes over MCP, hold the risky ones for your approval, and keep a secret-redacted journal that is tamper-evident with an ex...
|
81 % |
|
Open Docy: the open-source Agent OS for auditable AI agents
Free, open-source and self-hosted Agent OS from Docy AI. Build AI agents on a visual canvas, keep a person in the loop, and audit every decision.
|
81 % |
|
Trabecc — gateway and governance for MCP
Trust, but audit. Drop Trabecc between your AI agent and your MCP servers in 60 seconds. Default-deny policy, audit log, rate limits — without rewriting agen...
|
80 % |
|
Metatron — your codebase's conventions, versioned in git and consulted by AI agents
Metatron captures your team's real implementation decisions as versioned markdown in git, consulted by AI coding agents and curated through PR review — with...
|
80 % |
|
Enterprise AI gateway · AIGate
AIGate is a single Rust binary that sits in front of your model providers and enforces auth, budgets, and guardrails on every request before it's routed.
|
80 % |
|
ShiftLeft — MCP Gateway for Secure AI Tool Access
MCP Gateway enforces policy on every AI tool call. SBOM scanning, secrets detection, tool audit, and offline-capable signed policies — local stdio and HTTP....
|
80 % |
|
INFRO — AI gateway for routing, budgets and cost per request
Route, cap and track AI spend on the provider accounts you already own: automatic failover, budgets enforced before the call, cost per request, 0% markup.
|
80 % |
|
Proxilion: a reverse proxy for AI agents
Proxilion is a free, MIT-licensed, self-hosted reverse proxy that keeps AI agents inside their user's permissions. Runs in your own cloud. No API keys.
|
80 % |
|
PAIRL Gateway | Plug-In Replacement API Gateway for Agentic Workloads
PAIRL Gateway replaces plugin sprawl with one proxy-first API edge. Use prepaid credits, measure savings per request, and scale large agentic workloads.
|
80 % |
|
ActionGate — Intent Is Cheap. We Guard the Last Checkpoint.
OPA for AI actions. Composable enforcement primitives for autonomous AI agents. Rate limits, cost caps, and policy rules — evaluated in microseconds, before...
|
80 % |
Detected social media networks