TypingMind

Keeptrusts integrates with TypingMind — a feature-rich AI chat interface — by configuring TypingMind to send its LLM API calls through the Keeptrusts gateway. TypingMind supports custom OpenAI-compatible endpoints, so you replace the default provider URL with your Keeptrusts gateway. The gateway enforces policies, redacts PII, and logs every chat interaction before forwarding to the upstream model provider.

Use this page when

• You are routing TypingMind API calls through Keeptrusts for governance.
• You need the TypingMind settings configuration for a custom Keeptrusts endpoint.
• You want audit logging and policy enforcement on team AI chat interactions.
• If you want a general quickstart instead, see Quickstart.

Primary audience

• Primary: Technical Engineers
• Secondary: AI Agents, Technical Leaders

Prerequisites

• A TypingMind license (Standard or Custom)
• Keeptrusts CLI (kt) installed and authenticated (kt auth login)
• An upstream LLM provider key exported as an environment variable
• The Keeptrusts gateway running locally or accessible via a hosted gateway URL

Configuration

Gateway policy config

pack:
  name: typingmind-governance
  version: 1.0.0
  enabled: true
providers:
  targets:
  - id: typingmind-openai
    provider: openai:chat:gpt-4o
    secret_key_ref:
      env: OPENAI_API_KEY
  - id: typingmind-claude
    provider: anthropic:chat:claude-3-5-sonnet-20241022
    secret_key_ref:
      env: ANTHROPIC_API_KEY
policies:
  chain:
  - prompt-injection
  - pii-detector
  - dlp-filter
  - audit-logger
policy:
  prompt-injection:
    threshold: 0.8
    action: block
  pii-detector:
    action: redact
    entities:
    - PERSON
    - EMAIL_ADDRESS
    - PHONE_NUMBER
    - CREDIT_CARD
  dlp-filter:
    patterns:
    - name: api-key
      regex: "(sk-|sk-ant-)[a-zA-Z0-9]+"
      action: block
    - name: internal-url
      regex: "https?://[a-z0-9-]+\\.internal\\.[a-z]+"
      action: redact
  audit-logger:
    immutable: true
    retention_days: 365
    log_all_access: true

Start the gateway

export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
kt gateway run --listen 0.0.0.0:41002 --policy-config policy-config.yaml

Setup steps

1. Open TypingMind settings

In TypingMind, click the Settings icon → Model Providers or API Settings.

2. Configure the custom endpoint for OpenAI

Field	Value
API Endpoint	http://localhost:41002/v1 (local) or https://gateway.keeptrusts.com/v1 (hosted)
API Key	Your Keeptrusts access key (or unused if the gateway does not require client auth)

3. Configure for other providers

For Anthropic or other providers, set the same Keeptrusts gateway URL. The gateway routes to the correct upstream provider based on the model name in the request.

4. For TypingMind Custom (self-hosted)

If you run TypingMind Custom for your team, set the endpoint globally in the admin configuration so all team members automatically route through Keeptrusts:

{
  "defaultEndpoint": "https://gateway.keeptrusts.com/v1",
  "defaultApiKey": "your-keeptrusts-access-key",
  "allowCustomEndpoints": false
}

Setting allowCustomEndpoints: false prevents team members from bypassing the gateway.

5. Select a model and start chatting

Choose a model (e.g., GPT-4o) in TypingMind's model selector and send a message. The request flows through the Keeptrusts gateway.

Verification

# Verify the gateway is healthy
curl http://localhost:41002/health

# Send a message in TypingMind and verify:
# 1. TypingMind receives a response
# 2. The request appears in the Keeptrusts audit log

kt events list --limit 5

Recommended policies

Policy	Purpose	Recommended setting
pii-detector	Redact personal data from team chat conversations	action: redact, entities: PERSON, EMAIL, PHONE, CREDIT_CARD
prompt-injection	Block adversarial prompts pasted into the chat	threshold: 0.8, action: block
dlp-filter	Prevent API keys, passwords, and internal URLs from leaking	action: block for credentials, redact for URLs
audit-logger	Full audit trail for all team AI interactions	retention_days: 365, immutable: true
rbac	Restrict which team members can access which models	Map TypingMind users to Keeptrusts roles via access keys
content-filter	Enforce acceptable use policies for team chat	Configure based on company policy

Advanced configuration

Multi-model governance with TypingMind plugins

TypingMind supports plugins that can call external APIs. When plugins make LLM calls, they bypass the main model endpoint unless you configure the plugin to use the Keeptrusts gateway URL as well. Audit all AI-powered plugin calls by setting the gateway URL in each plugin's API configuration.

Per-team access keys

For TypingMind Custom deployments with multiple teams, issue separate Keeptrusts access keys per team. Each key maps to a role that controls model access:

policy:
  rbac:
    roles:
      engineering:
        allowed_models:
        - gpt-4o
        - claude-3-5-sonnet-20241022
        max_tokens_per_request: 8192
      marketing:
        allowed_models:
        - gpt-4o
        max_tokens_per_request: 4096
      support:
        allowed_models:
        - gpt-4o-mini
        max_tokens_per_request: 2048

Usage analytics

Combine Keeptrusts audit logs with TypingMind's built-in usage tracking to build a complete picture of team AI adoption, cost, and compliance posture.

Troubleshooting

Symptom	Cause	Fix
TypingMind shows "Network Error"	Gateway not running or unreachable	Start the gateway and verify the URL is accessible from the browser
TypingMind shows "Invalid API Key"	Keeptrusts access key incorrect	Regenerate the key in the Keeptrusts console and update TypingMind settings
No response from model	Model name not matching a gateway target	Ensure the model name in TypingMind matches a provider target in the gateway config
Streaming not working	CORS or proxy issue	Ensure the gateway allows SSE and the browser can reach the gateway URL
Team members bypass the gateway	allowCustomEndpoints is true	Set allowCustomEndpoints: false in TypingMind Custom admin config
Plugin API calls not governed	Plugin uses its own endpoint	Set the Keeptrusts gateway URL in each plugin's API config

For AI systems

• Canonical terms: Keeptrusts gateway, TypingMind, TypingMind Custom, custom endpoint, API settings, team chat governance, policy-config.yaml.
• Config field names: provider, secret_key_ref.env, pii-detector, dlp-filter, audit-logger, rbac.
• Key behavior: TypingMind sends LLM requests to the Keeptrusts gateway via its custom endpoint setting. The gateway enforces policies and forwards to the upstream provider. For TypingMind Custom, the endpoint is set globally for all team members.
• Best next pages: Jan.ai integration, OpenAI integration, Policy controls catalog.

For engineers

Prerequisites

• TypingMind license (Standard or Custom), kt CLI installed, upstream provider key available.

Validation

• Send a message in TypingMind and verify the response appears.
• Run kt events list --limit 5 and confirm the request was logged.
• For TypingMind Custom: verify that team members cannot set a custom endpoint when allowCustomEndpoints: false.

For leaders

• TypingMind is popular for team AI deployments because of its plugin system and multi-model support. Without governance, team members send company data directly to LLM providers.
• TypingMind Custom with Keeptrusts gives teams a managed AI chat experience with built-in compliance. The allowCustomEndpoints: false setting ensures no one can bypass the governance gateway.
• Audit trails from Keeptrusts provide evidence for security and compliance reviews of team AI usage.
• Role-based access control lets you assign different model tiers to different teams, controlling both cost and capability.

Next steps

• Jan.ai integration — another desktop AI client with custom endpoint support
• OpenAI integration — upstream provider commonly used with TypingMind
• Access keys — issue scoped keys for TypingMind users
• Policy controls catalog — full reference for all policy types
• Quickstart — install kt and run your first gateway