docs(readme): reframe intro + list all 25 supported providers

Kigi started as an unofficial Kimi Code CLI community build; by request it
now works with 25 providers. Replace the stale three-platform table with the
full supported list (Kimi Code OAuth + 24 API-key providers, each with its
platform id and env var). Unsupported/not-yet-built providers are omitted.
This commit is contained in:
2026-07-21 20:30:53 -04:00
parent bc4e76db96
commit 8a26460251
+63 -28
View File
@@ -8,13 +8,17 @@
autonomous, self-verifying agent loops — planned, parallelized, autonomous, self-verifying agent loops — planned, parallelized,
adversarially verified, and merged back, end to end.</p> adversarially verified, and merged back, end to end.</p>
**Kigi** is an unofficial Kimi Code CLI community build — a terminal-based **Kigi** started as an unofficial Kimi Code CLI community build, a
AI coding agent re-targeted at the Kimi Code subscription API and the terminal-based AI coding agent re-targeted at the Kimi Code subscription API,
Moonshot open platform, built on the Apache-2.0 sources of built on the Apache-2.0 sources of
[xai-org/grok-build](https://github.com/xai-org/grok-build). [xai-org/grok-build](https://github.com/xai-org/grok-build). It first shipped
wired to Kimi Code and the Moonshot open platform. By request, it now works
with 25 providers: OpenAI, Anthropic, Google, xAI, Groq, Cerebras, OpenRouter,
MiniMax, Z.AI, Qwen, Xiaomi, and more. The full list is under
[Providers and API keys](#providers-and-api-keys).
It runs as a full-screen TUI that understands your codebase, edits files, It runs as a full-screen TUI that understands your codebase, edits files,
executes shell commands, searches the web, and manages long-running tasks executes shell commands, searches the web, and manages long-running tasks,
interactively, headlessly for scripting/CI, or embedded in editors via the interactively, headlessly for scripting/CI, or embedded in editors via the
Agent Client Protocol (ACP). Agent Client Protocol (ACP).
@@ -107,48 +111,79 @@ echo 'export KIGI_GRAPH=0' >> ~/.zshrc # or ~/.bashrc / ~/.bash_profile
## Providers and API keys ## Providers and API keys
Kigi talks to a fixed three-platform registry: Kigi ships a fixed registry of 25 platforms: the Kimi Code subscription plus
24 API-key providers. There is no dynamic provider registration; each is a
compiled-in spec.
| Platform id | Base URL | Auth | **Kimi Code** (the original target) uses subscription OAuth, not an API key:
| ------------- | -------------------------------- | --------------------------- |
| `kimi-code` | `https://api.kimi.com/coding/v1` | Kimi Code subscription OAuth (`kigi login`) |
| `moonshot-cn` | `https://api.moonshot.cn/v1` | Moonshot open-platform API key |
| `moonshot-ai` | `https://api.moonshot.ai/v1` | Moonshot open-platform API key |
Moonshot API keys come from the environment or `~/.kigi/config.toml` | Platform id | Base URL | Auth |
(environment wins; values are never logged): | ----------- | -------------------------------- | ------------------------------------------- |
| `kimi-code` | `https://api.kimi.com/coding/v1` | Kimi Code subscription OAuth (`kigi login`) |
**API-key providers.** Set the provider's env var, or put the key in
`~/.kigi/config.toml` under `[platforms.<id>]`. The environment wins, a
platform-scoped name beats a generic one, and keys are never logged.
| Provider | Platform id | API key env |
| ------------------------- | ---------------------- | ----------------------------------------------- |
| Moonshot (moonshot.cn) | `moonshot-cn` | `KIGI_MOONSHOT_CN_API_KEY` (or `KIGI_MOONSHOT_API_KEY`) |
| Moonshot (moonshot.ai) | `moonshot-ai` | `KIGI_MOONSHOT_AI_API_KEY` (or `KIGI_MOONSHOT_API_KEY`) |
| OpenAI | `openai` | `OPENAI_API_KEY` |
| Anthropic | `anthropic` | `ANTHROPIC_API_KEY` |
| DeepSeek | `deepseek` | `DEEPSEEK_API_KEY` |
| Groq | `groq` | `GROQ_API_KEY` |
| Mistral | `mistral` | `MISTRAL_API_KEY` |
| Fireworks AI | `fireworks` | `FIREWORKS_API_KEY` |
| Google Gemini | `google` | `GEMINI_API_KEY` |
| OpenRouter | `openrouter` | `OPENROUTER_API_KEY` |
| Together AI | `together` | `TOGETHER_API_KEY` |
| Cerebras | `cerebras` | `CEREBRAS_API_KEY` |
| NVIDIA NIM | `nvidia` | `NVIDIA_API_KEY` |
| Vercel AI Gateway | `vercel-ai-gateway` | `AI_GATEWAY_API_KEY` |
| xAI (Grok) | `xai` | `XAI_API_KEY` |
| Qwen Token Plan | `qwen-token-plan` | `QWEN_TOKEN_PLAN_API_KEY` |
| Qwen Token Plan (China) | `qwen-token-plan-cn` | `QWEN_TOKEN_PLAN_CN_API_KEY` |
| Kimi For Coding | `kimi-coding` | `KIMI_API_KEY` |
| Z.AI | `zai` | `ZAI_API_KEY` |
| Z.AI Coding (China) | `zai-coding-cn` | `ZAI_CODING_CN_API_KEY` |
| Xiaomi MiMo | `xiaomi` | `XIAOMI_API_KEY` |
| Xiaomi Token Plan (China) | `xiaomi-token-plan-cn` | `XIAOMI_TOKEN_PLAN_CN_API_KEY` |
| MiniMax | `minimax` | `MINIMAX_API_KEY` |
| MiniMax (China) | `minimax-cn` | `MINIMAX_CN_API_KEY` |
```sh ```sh
export KIGI_MOONSHOT_API_KEY=sk-... # applies to both open platforms export OPENAI_API_KEY=sk-...
export KIGI_MOONSHOT_CN_API_KEY=sk-... # platform-scoped, beats the generic name export XAI_API_KEY=xai-...
export KIGI_MOONSHOT_AI_API_KEY=sk-...
``` ```
```toml ```toml
# ~/.kigi/config.toml # ~/.kigi/config.toml
[platforms.moonshot-cn] [platforms.openai]
api_key = "sk-..." api_key = "sk-..."
[platforms.moonshot-ai] [platforms.xai]
api_key = "sk-..." api_key = "xai-..."
``` ```
On login and on startup Kigi syncs each configured platform's model list On login and on startup Kigi syncs each configured platform's model list
from `GET {base}/models` and shows the merged catalog in the model picker from `GET {base}/models` and shows the merged catalog in the model picker
(catalog keys are `{platform_id}/{model_id}`). Models that advertise (catalog keys are `{platform_id}/{model_id}`). Model metadata (context
selectable thinking levels (e.g. K3's `low`/`high`/`max`) expose them in window, thinking levels) comes from the live listing when the provider
`/model` and `/effort`. If the sync fails, the last cached catalog is used; serves it, otherwise from a bundled models.dev snapshot. Models that
with no cache, a small built-in fallback list applies. Model selection advertise selectable thinking levels (e.g. K3's `low`/`high`/`max`) expose
them in `/model` and `/effort`. If the sync fails, the last cached catalog is
used; with no cache, a small built-in fallback list applies. Model selection
resolves as `--model` CLI flag > `KIGI_DEFAULT_MODEL` > `[models] default` resolves as `--model` CLI flag > `KIGI_DEFAULT_MODEL` > `[models] default`
in config.toml > server-delivered list > built-in fallback. in config.toml > server-delivered list > built-in fallback.
`KIGI_CODE_BASE_URL` re-points the subscription platform (useful for Each platform's base URL can be re-pointed for dev/test with
testing); `KIGI_MOONSHOT_CN_BASE_URL` / `KIGI_MOONSHOT_AI_BASE_URL` are the `KIGI_<PLATFORM>_BASE_URL` (e.g. `KIGI_CODE_BASE_URL`,
equivalent dev/test overrides for the open platforms. `KIGI_MOONSHOT_CN_BASE_URL`, `KIGI_OPENAI_BASE_URL`).
The web `search`/`fetch` tools ride the Kimi Code subscription services and The web `search`/`fetch` tools ride the Kimi Code subscription services and
are present only on OAuth sessions API-key-only sessions run without are present only on OAuth sessions. API-key-only sessions run without them,
them, matching the official client. matching the official client.
## Building from source ## Building from source