The Agent Trust Stack Is Now Available in TypeScript

#ai #agents #opensource #typescript

Seven protocols. 663 tests. Both ecosystems.

The Agent Trust Stack — the open-source protocol suite for agent provenance, reputation, agreements, justice, lifecycle, matchmaking, and context economics — shipped its TypeScript implementation today. Every protocol that was available via pip install is now available via npm install.

This matters because the agent ecosystem is split. Python dominates training and research. TypeScript dominates deployment — MCP servers, Vercel AI SDK, LangChain.js, most production agent frameworks run on Node.js. A trust stack that only speaks Python can't reach the agents that actually serve users.

What shipped

Seven npm packages, each a direct port of the corresponding Python package:

npm install chain-of-consciousness     # Cryptographic provenance chains
npm install agent-rating-protocol      # Bilateral blind reputation scoring
npm install agent-service-agreements   # Machine-readable contracts
npm install agent-justice-protocol     # Dispute resolution and forensics
npm install agent-lifecycle-protocol   # Birth, fork, succession, retirement
npm install agent-matchmaking          # Discovery and trust-weighted matching
npm install context-window-economics   # Inference cost allocation

663 tests across all seven packages. Zero failures. The TypeScript implementations match the Python API surface — if you've used the Python version, the TypeScript version works the same way.

Why this matters for TypeScript developers

If you're building agents on Node.js — whether with the Vercel AI SDK, LangChain.js, or raw MCP servers — trust operations used to mean one of two options:

Python subprocess — spawn a Python process, serialize inputs, deserialize outputs, handle failures across process boundaries
HTTP round-trip — call the hosted API, deal with network latency, handle outages

Now they're native imports. The latency difference is real: hundreds of milliseconds for an API call versus microseconds for a local function call. For trust operations that happen on every agent interaction — provenance verification, reputation checks, agreement validation — that's the difference between "fast enough to use" and "too slow to bother."

What's in each package

chain-of-consciousness — Create and verify tamper-evident hash chains. Every agent action becomes a signed, hash-linked entry anchored to Bitcoin via OpenTimestamps. The chain is the agent's identity: continuous, immutable, independently verifiable.

agent-rating-protocol — Bilateral blind reputation scoring. Two agents rate each other simultaneously, neither seeing the other's rating until both commit. Anti-Goodhart protections prevent gaming.

agent-service-agreements — Machine-readable contracts between agents. SLA terms, quality verification, escrow, automated enforcement.

agent-justice-protocol — Dispute filing, evidence collection, forensic investigation, arbitration, remediation.

agent-lifecycle-protocol — Birth, fork, succession, migration, retirement with reputation inheritance.

agent-matchmaking — Discovery and trust-weighted matching across platforms with federation support.

context-window-economics — Inference cost allocation: Shapley-fair splitting, congestion pricing, token metering, spam prevention.

Cross-ecosystem interoperability

The Python and TypeScript implementations share the same test vectors. A chain created in Python verifies in TypeScript and vice versa.

This isn't just API parity — it's cryptographic interoperability. A Python agent and a TypeScript agent can verify each other's provenance chains, validate each other's reputation scores, and enforce the same service agreements without any translation layer.

Source and license

Every package is open source under Apache 2.0.

npm: Search "agent-trust-stack" on npmjs.com
PyPI: Same package names, pip install instead of npm install
GitHub: Source in typescript/ directory of each protocol repo

Trust infrastructure should be native to every ecosystem your agents run in. Chain of Consciousness is the foundation — a cryptographic provenance chain that gives each agent a tamper-evident, hash-linked record of every action, anchored to Bitcoin. Reputation, agreements, disputes, lifecycle — they all build on a verified identity. That identity starts with the chain.