|
TENEX — Multi-Agent Infrastructure on Nostr
Agents that remember. Identity you can verify. A memory + identity layer that plugs under existing frameworks.
|
81 % |
|
Obsign: audit proof of AI agent actions | DORA & NIS2
Enforceable audit log of AI agent actions: who delegated what, to which agent, with which policy verdict. Sealed, verifiable offline. For DORA and NIS2.
|
81 % |
|
AxiNode – Zero-Credential Control Plane
AxiNode is a secure, agent-based control plane that replaces SSH with signed commands, mTLS agents, and full audit trails.
|
80 % |
|
Network-AI | Multi-Agent Orchestration for Production Systems
Network-AI is a TypeScript/Node.js multi-agent orchestration layer with shared-state locking, permission gating, audit trails, FSM governance, and 32 framewo...
|
80 % |
|
RCPT Protocol — Receipt Chain Protocol for Trust
An open cryptographic standard for verifiable agent action receipts — signed, timestamped, tamper-evident records that any agent can generate and any system...
|
80 % |
|
QUORBIT — Trust layer for AI agents
|
80 % |
|
AuthPlane | Open-Source OAuth 2.1 Authorization Server for MCP
AuthPlane is a self-hosted OAuth 2.1 authorization server for MCP servers. Open source, spec-compliant, one Go binary. Add production-grade MCP authenticatio...
|
80 % |
|
Give AI tools approved infrastructure actions, not SSH · emisar
One governed MCP server connects any AI agent to a finite action catalog, enforced on-host with pack trust, policy gates, approvals, and an audit trail.
|
80 % |
|
Trust Graduation Protocol
Trust Graduation is a permission protocol for agentic systems. Agents earn permission per action class through evidence, approval packets, and receipts.
|
80 % |
|
OpenGrid — independent operators, unified by protocol
The AI Grid brings compute from independent providers into one intelligent network. Each request is placed by capacity, reputation, and locality, and verifie...
|
80 % |
|
OrcaCyber — cyber harness for defenders
The autonomous cyber harness for defenders. Proven, not guessed. Currently in private testing.
|
80 % |
|
Krahanos | Agent security, made visible
Scan Python agent repositories for dangerous capabilities before they run.
|
80 % |
|
0200project, Machine-native tools for AI agents
base-transaction-decoder explains any Base transaction, and tells your agent which fields an attacker controls and when a safety check did not run. Per call...
|
80 % |
|
Raucle — Verifiable Agent Accountability
Raucle produces a cryptographic record of every action your AI agents take — independently verifiable, exportable to auditors, and built for the audit-loggin...
|
79 % |
|
Trit
Trit is a self-hosted development workspace for coding agents.
|
79 % |
|
Sphyr · A firewall for outbound agent requests
Signed requests. Receipts on every call. Route your agent's outbound traffic through Sphyr for cryptographic identity, tamper-evident audit trails, and per-k...
|
79 % |
|
Coproduct — the provable-coordination extension of A2A v1.0
Every AI agent response carries a cryptographically-signed provenance manifest. Race conditions fail at the type level. Audit trails compose by construction....
|
79 % |
|
AI Authorization Layer for Agents | Permission Protocol
Control AI agent actions with policy checks and human approval. Add authorization to configured MCP tool calls and GitHub workflows, with records for review.
|
79 % |
|
Never-Leak Protocol — The Open Standard for AI Agent Secret Security
NL Protocol is an open specification that defines how AI agents interact with secrets without those secrets ever entering the agent's context window. Agents...
|
79 % |
|
ProofTrail — Tamper-proof receipts for AI agents
Cryptographic audit trails for AI agent tool calls. One decorator. Zero dependencies. Receipts that can't be forged.
|
79 % |
Detected social media networks