trust — salud del software de código abierto

npm · Go · crates.io

96Excepcionalíndice de salud

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Python★ 6138↓ 14.7K/mes28 ago 2026

MIT28 ago 2026 · métricas 2.10.0

npm · crates.io

90Excelenteíndice de salud

aeoess/agent-passport-system

Open protocol for AI agent accountability. Cryptographic identity, scoped delegation that narrows per hop, gateway enforcement, signed receipts for every action. TypeScript reference, Apache-2.0.

TypeScript★ 45↓ 2434/mes10 sept 2026

Apache-2.010 sept 2026 · métricas 2.10.0

87Excelenteíndice de salud

pilot-protocol/pilotprotocol

Pilot Protocol: The Internet of Agents

Go · Shell★ 13813 sept 2026

AGPL-3.013 sept 2026 · métricas 2.10.0

PyPI · npm · crates.io +1

86Excelenteíndice de salud

QWED-AI/qwed-verification

Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.

Python★ 58↓ 764/mes18 sept 2026

Apache-2.018 sept 2026 · métricas 2.10.0

npm

86Excelenteíndice de salud

emiliaprotocol/emilia-protocol

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

TypeScript · HTML★ 612↓ 597/mes22 oct 2026

Apache-2.022 oct 2026 · métricas 2.10.0

PyPI

84Excelenteíndice de salud

agentrust-io/agent-manifest

Agent Manifest SDK. Hardware-anchors all 10 artifacts defining an agent at deployment. Python and TypeScript.

Python★ 19↓ 4734/mes15 sept 2026

Apache-2.015 sept 2026 · métricas 2.10.0

PyPI

80Excelenteíndice de salud

agentscore/python-commerce

AgentScore Commerce — Python merchant SDK for agent commerce: identity, payment, discovery, Stripe multichain.

Python★ 0↓ 1555/mes16 sept 2026

MIT16 sept 2026 · métricas 2.10.0

PyPI · npm

80Excelenteíndice de salud

alizahidraja/isnad

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

Python★ 53↓ 2089/mes21 oct 2026

Apache-2.021 oct 2026 · métricas 2.10.0

PyPI · Maven

80Excelenteíndice de salud

jawah/wassima

No more certifi! System trust store at hand. In Pure Python.

Python★ 24↓ 1.4M/mes20 oct 2026

MIT20 oct 2026 · métricas 2.10.0

PyPI · npm

80Excelenteíndice de salud

smilinTux/skcapstone

SKCapstone — The sovereign agent framework. CapAuth backbone. Cloud 9 trust. SKMemory persistence. Same agent, same bond, same context — everywhere. Runs from ~/.

Python★ 1↓ 24.5K/mes12 sept 2026

GPL-3.012 sept 2026 · métricas 2.10.0

npm · crates.io · Go

80Excelenteíndice de salud

zerkerlabs/treeship

Portable trust receipts for agent workflows. Signed, chained, verifiable.

Rust★ 13↓ 10.2K/mes1 oct 2026

Apache-2.01 oct 2026 · métricas 2.10.0

crates.io · npm

78Buenoíndice de salud

agentidentitytrustprotocol/aitp-rs

El repositorio no publica descripción.

Rust★ 0↓ 15.5K/mes20 oct 2026

Apache-2.020 oct 2026 · métricas 2.10.0

npm

75Buenoíndice de salud

forgesworn/bray

Trust-aware Nostr MCP server for AI agents and humans. Verification, proximity, and access woven into every interaction.

TypeScript★ 1↓ 2135/mes13 sept 2026

MIT13 sept 2026 · métricas 2.10.0

73Buenoíndice de salud

pilot-protocol/trustedagents

Pilot Protocol trusted-agents plugin — embedded auto-trust allowlist + IsTrusted() gate

Go★ 020 oct 2026

AGPL-3.020 oct 2026 · métricas 2.10.0

crates.io · PyPI

71Buenoíndice de salud

dp-web4/web4

Web4: an open standard for verifiable AI presence — LCT identity, T3/V3 trust tensors, MRH context, ATP/ADP. Rust + Python SDKs on crates.io/PyPI. AGPL-3.0-or-later.

Python★ 12↓ 70/mes19 sept 2026

AGPL-3.019 sept 2026 · métricas 2.10.0

npm

71Buenoíndice de salud

polygraphso/litmus

Behavioral litmus harness for MCP servers — the open @polygraphso/litmus package (CLI, library, MCP server).

TypeScript★ 8↓ 350/mes14 sept 2026

Apache-2.014 sept 2026 · métricas 2.10.0

PyPI

69Buenoíndice de salud

veldtlabs/veldt-kya

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

Python★ 3↓ 5683/mes8 sept 2026

Licencia propia8 sept 2026 · métricas 2.10.0

PyPI

65Buenoíndice de salud

YugantM/hvtracker

AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.

HTML★ 513 sept 2026

MIT13 sept 2026 · métricas 2.10.0

65Buenoíndice de salud

pilot-protocol/handshake

Pilot Protocol handshake plugin — node-to-node trust negotiation, accept/deny flow, trust persistence (port 444)

Go★ 022 oct 2026

AGPL-3.022 oct 2026 · métricas 2.10.0

npm · PyPI

63Moderadoíndice de salud

maxfain/basedagents

An open registry for discovering, verifying, and trusting AI agents.

TypeScript★ 0↓ 913/mes16 sept 2026

Apache-2.016 sept 2026 · métricas 2.10.0

PyPI

62Moderadoíndice de salud

veracium-ai/Veracium

Provenance-aware memory for AI agents.

Python★ 9↓ 3182/mes15 sept 2026

MIT15 sept 2026 · métricas 2.10.0

npm

60Moderadoíndice de salud

dot-skill/skillerr

Open .skill Protocol - a sealed, inspectable package format for AI agent skills. Reference implementation: skillerr.

TypeScript · JavaScript★ 3↓ 774/mes14 sept 2026

Apache-2.014 sept 2026 · métricas 2.10.0

npm

59Moderadoíndice de salud

hachure-org/spec

Hachure — an open trust format. Specification, normative schemas, and conformance test vectors. npm: hachure

JavaScript★ 0↓ 29.8K/mes12 sept 2026

MIT12 sept 2026 · métricas 2.10.0

PyPI

57Moderadoíndice de salud

MoltyCel/moltrust-mcp-server

MCP server for MolTrust — Trust Infrastructure for AI Agents

Python★ 4↓ 2689/mes20 oct 2026

MIT20 oct 2026 · métricas 2.10.0

npm · PyPI

54Moderadoíndice de salud

YugantM/hvtracker-mcp

MCP server for HVTracker trust checks.

Python · JavaScript★ 1↓ 520/mes13 sept 2026

MIT13 sept 2026 · métricas 2.10.0

npm

54Moderadoíndice de salud

davidnichols-ops/trustcard

Cryptographic trust infrastructure for MCP servers — signed manifests, TOFU pinning, two-gate enforcement, and the "npm audit" scanner.

JavaScript★ 4↓ 1290/mes13 sept 2026

MIT13 sept 2026 · métricas 2.10.0

34En riesgoíndice de salud

dedis/cothority

Scalable collective authority

Go★ 43017 oct 2026

Licencia propia17 oct 2026 · métricas 2.10.0

npm

34En riesgoíndice de salud

lemmaflow/lemmaflow

Trust engine for production software. Free local scans for PII, secrets, privacy, GDPR and data retention — plus an AI-native audit. npx -y lemmaflow scan

JavaScript★ 221 sept 2026

Apache-2.021 sept 2026 · métricas 2.10.0

npm

34En riesgoíndice de salud