Commit Graph

15 Commits (4329d94de3a71803db177ee50af68eb75d7ea06b)

Author SHA1 Message Date
Vincent Koc 8ac4b09fa4 docs: fix em-dash headings and broken links across docs
- Replace em-dashes in headings with hyphens/parens (breaks Mintlify anchors)
- Fix broken /testing link in pi-dev.md to /help/testing
- Convert absolute docs URLs to root-relative in pi-dev.md

Files: migrating.md, images.md, audio.md, media-understanding.md,
venice.md, minimax.md, AGENTS.default.md, security/index.md, pi-dev.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
8 months ago
Peter Steinberger f9e185887f docs: restore onboard docs references 8 months ago
Peter Steinberger 823039c000
docs: prefer setup wizard command 8 months ago
Vincent Koc 3070fafec1
fix(venice): switch default model to kimi-k2-5 (#38423)
* Docs: refresh Venice default model guidance

* Venice: switch default model to Kimi K2.5

* Changelog: credit Venice default refresh
9 months ago
Peter Steinberger 6b85ec3022 docs: tighten subscription guidance and update MiniMax M2.5 refs 9 months ago
Peter Steinberger eb35fb745d docs: remove provider recommendation language 9 months ago
Peter Steinberger 6fef318fda docs: replace legacy chat examples in Venice provider guide 9 months ago
Seb Slight abcaa8c7a9
Docs: add nav titles across docs (#5689) 10 months ago
cpojer 8cab78abbc
chore: Run `pnpm format:fix`. 10 months ago
Peter Steinberger 9a7160786a refactor: rename to openclaw 10 months ago
jonisjongithub fdcac0ccf4
fix: correct 'Venius' typo to 'Venice' in provider docs (#3638) - thanks (@jonisjongithub) 10 months ago
Peter Steinberger 6d16a658e5 refactor: rename clawdbot to moltbot with legacy compat 10 months ago
Peter Steinberger b9dc117309 docs: refine venice highlight 10 months ago
jonisjongithub 25f2d2adb3 docs: remove rate limits claim from Venice docs 10 months ago
jonisjongithub 7540d1e8c1 feat: add Venice AI provider integration
Venice AI is a privacy-focused AI inference provider with support for
uncensored models and access to major proprietary models via their
anonymized proxy.

This integration adds:

- Complete model catalog with 25 models:
  - 15 private models (Llama, Qwen, DeepSeek, Venice Uncensored, etc.)
  - 10 anonymized models (Claude, GPT-5.2, Gemini, Grok, Kimi, MiniMax)
- Auto-discovery from Venice API with fallback to static catalog
- VENICE_API_KEY environment variable support
- Interactive onboarding via 'venice-api-key' auth choice
- Model selection prompt showing all available Venice models
- Provider auto-registration when API key is detected
- Comprehensive documentation covering:
  - Privacy modes (private vs anonymized)
  - All 25 models with context windows and features
  - Streaming, function calling, and vision support
  - Model selection recommendations

Privacy modes:
- Private: Fully private, no logging (open-source models)
- Anonymized: Proxied through Venice (proprietary models)

Default model: venice/llama-3.3-70b (good balance of capability + privacy)
Venice API: https://api.venice.ai/api/v1 (OpenAI-compatible)
10 months ago