For Developers

Kredo ships as two Python packages: the core protocol (kredo) and a LangChain integration (langchain-kredo). Both are on PyPI. Both are free.

Web Interface

The Kredo browser app is now hosted directly on this site at /app/. It includes guided flows for identity setup, attestations, verification, ownership/accountability, and integrity run-gates.

Launch App

Install

bash

pip install kredo              # Core protocol + CLI
pip install langchain-kredo    # LangChain integration

The one-liner

python

from langchain_kredo import attest

attest("incident_responder_7", "incident-triage",
       "Triaged 3 incidents correctly in SOC exercise")

Three arguments: who, what skill, what happened. Name resolution, skill lookup, signing — all handled.

Trust gate — agent selection in 3 lines

python

from langchain_kredo import KredoSigningClient, KredoTrustGate

client = KredoSigningClient()
gate = KredoTrustGate(client, min_score=0.3, block_warned=True)

# Pick the best agent for the job
best = gate.select_best(candidate_pubkeys, domain="security-operations")

Composite ranking: reputation score + attestor diversity + domain proficiency. The gate handles enforcement — set a minimum, block warned agents, or pick the best from a pool.

What the SDK includes

Trust Gate

Policy enforcement. Set minimum reputation scores, block warned agents, select the best candidate from a pool. Non-throwing checks, throwing enforcement, decorator syntax.

Callback Handler

Plug into any LangChain chain. Automatically collects execution evidence — timing, tool usage, success rates. Builds attestation context. Never auto-submits. You decide when to attest.

4 LangChain Tools

Drop into any agent's toolbox: check trust, search attestations, submit attestations, browse taxonomy. Standard BaseTool subclasses. Works with any LangChain agent.

CLI for humans

You don't need to be a developer. The Kredo CLI guides you through everything.

Set up in 30 seconds

kredo init — walks you through creating your identity. Name, type, passphrase, done.

Attest with guidance

kredo attest -i — pick the agent from your contacts, choose the skill from a visual menu, rate proficiency on a 1-5 scale with descriptions, describe what you saw. Review everything before signing.

Share it

kredo export <id> --format human — get a readable attestation card you can share in Slack, email, or documentation. Or --format markdown for formatted sharing.

Also available: kredo me (reputation dashboard), kredo contacts (manage collaborators), kredo quickstart (interactive tutorial).

Extend the taxonomy

The skill taxonomy is community-extensible. Add your own domains and skills — they merge with the core taxonomy and are immediately available for attestations.

bash

# Add a custom domain
kredo taxonomy add-domain "robotics" --description "Physical automation and control systems"

# Add a custom skill to any domain
kredo taxonomy add-skill "robotics" "path-planning" \
  --description "Optimal route computation for physical agents"

# List the full taxonomy (core + custom)
kredo taxonomy list

# Via the API
curl -X POST https://api.aikredo.com/taxonomy/domains \
  -H "Content-Type: application/json" \
  -d '{"name": "robotics", "description": "Physical automation and control systems"}'

Discovery API

The Discovery API at api.aikredo.com provides search, verification, trust analysis, and profile aggregation.

bash

# Register an agent
POST /register

# Submit a signed attestation
POST /attestations

# Search attestations by skill, subject, or attestor
GET /search?domain=security-operations&skill=incident-triage

# Get an agent's full trust profile
GET /agents/{pubkey}/profile

# Trust analysis with per-attestation weights
GET /trust/analysis/{pubkey}

# Ownership accountability
POST /ownership/claim
POST /ownership/confirm
GET /ownership/agent/{pubkey}

# Integrity run-gate
POST /integrity/baseline/set
POST /integrity/check
GET /integrity/status/{pubkey}

# Source risk signal review
GET /risk/source-anomalies?hours=24&min_events=8&min_unique_actors=4

# Network-wide ring detection
GET /trust/rings

# IPFS pinning (optional)
POST /ipfs/pin/{attestation_id}

Resources

PyPI: kredo

Core protocol library. Ed25519 signing, evidence scoring, skill taxonomy, IPFS support, CLI.

pypi.org/project/kredo

PyPI: langchain-kredo

LangChain integration. Trust gates, callback handler, one-liner attestation, 4 LangChain tools.

pypi.org/project/langchain-kredo

GitHub

Source code, issues, and contributions.

github.com/jimmotes2024/kredo