ZacharyZhang-NY
f825132983
The 13th registry row: id "cerebras", CEREBRAS_API_KEY > auth.json "cerebras" scope, https://api.cerebras.ai/v1 with KIGI_CEREBRAS_BASE_URL override, Bearer, ChatCompletions, enrichment-backed metadata (models_dev_id cerebras). Cerebras' catalog is all chat LLMs (no embedding/tts pollution) and its /models is minimal (ids only), so restrict_to_enriched=FALSE: keep every live model, enrich the known ones (context + effort menus low/medium/high), unknown ones keep the default context. The e2e pins this enrich-without- restrict path (new — prior enrichment providers all used restrict=true). Review caught a likely-DOA defect: Cerebras uses strict additionalProperties:false validation (confirmed 400-rejecting store, maxTokens, thinking, nested reasoning_content), and stream_options is not in its schema — so Passthrough (which keeps the stream_options.include_usage kigi injects on every streaming request) would very likely 400 all streaming. Generalized ChatCompat::Mistral -> ChatCompat::StrictOpenAi (serde alias "mistral" keeps pre-rename persisted sessions loading), which strips stream_options + private fields for any strict OpenAI-compat validator; both Mistral and Cerebras now map to it. Future strict-validator candidates (NVIDIA/Azure/Xiaomi/OpenCode) noted for the same check. reasoning_effort (incl. "none") passes through; /v1/models requires auth so key validation works; console cloud.cerebras.ai.
Kigi (kigi) 🌘
🕸️ The world's first CLI with built-in Graph Engineering
/graph turns one objective into a dependency graph of
autonomous, self-verifying agent loops — planned, parallelized,
adversarially verified, and merged back, end to end.
Kigi is an unofficial Kimi Code CLI community build — a terminal-based AI coding agent re-targeted at the Kimi Code subscription API and the Moonshot open platform, built on the Apache-2.0 sources of xai-org/grok-build.
It runs as a full-screen TUI that understands your codebase, edits files, executes shell commands, searches the web, and manages long-running tasks — interactively, headlessly for scripting/CI, or embedded in editors via the Agent Client Protocol (ACP).
Installation · Graph engineering · Providers and API keys · Building from source · Coexistence with the official CLI · License
Installation
Prebuilt single-file binaries for macOS (arm64/x86_64), Linux (arm64/x86_64), and Windows (x86_64) are published on GitHub Releases:
# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/ZacharyZhang-NY/Kigi-CLI/main/install.sh | bash
# Windows PowerShell
irm https://raw.githubusercontent.com/ZacharyZhang-NY/Kigi-CLI/main/install.ps1 | iex
kigi --version # kigi 0.1.1 … unofficial Kimi Code CLI community build
kigi login # sign in with your Kimi Code subscription (device-code flow)
kigi # start the TUI
The installer verifies every download against the release's SHA256SUMS,
installs into ~/.kigi/bin/kigi (%USERPROFILE%\.kigi\bin\kigi.exe on
Windows), persists the PATH line for you, and enables graph engineering
by default (KIGI_GRAPH=1; see Graph engineering
to disable). Later releases arrive through the
built-in self-updater (kigi update, gated by KIGI_AUTO_UPDATE), which
pulls from the same GitHub Releases feed.
Graph engineering
Kigi is the first CLI to ship graph engineering as a first-class command: where a loop drives one agent, a graph is the programmable organization connecting many.
/graph <objective> [--budget <tokens>] # decompose + run fully autonomously
/graph status # node tree, budget, current work
/graph show # box-drawing DAG view
/graph pause | resume [--budget <n>] # halt / continue (budget top-up)
/graph clear # abandon the graph
One /graph <objective> runs the whole closed loop: a planner subagent
decomposes the objective into a validated dependency DAG; independent
nodes fan out as parallel workers in isolated git worktrees, each gated
by an adversarial verifier and merged back three-way; out-of-scope
discoveries (DISCOVERED:) replan the graph append-only; a topology
optimizer prunes false dependencies at plan boundaries; and a terminal
verification node re-checks the whole objective before the graph
completes. State follows your repo in .kigi/graph.jsonl, so a fresh
session — or a teammate — can /graph resume where you left off.
The installer enables it by default. To disable:
# macOS / Linux
echo 'export KIGI_GRAPH=0' >> ~/.zshrc # or ~/.bashrc / ~/.bash_profile
# Windows PowerShell
[Environment]::SetEnvironmentVariable('KIGI_GRAPH','0','User')
(One-off instead: KIGI_GRAPH=0 kigi.) Tuning knobs:
KIGI_GRAPH_CONCURRENCY (parallel nodes, default 3),
KIGI_GRAPH_NODE_ROUNDS (worker↔verifier rounds per node, default 3),
KIGI_GRAPH_REPLAN_CAP (replan passes, default 3),
KIGI_GRAPH_OPTIMIZER=0 (disable the optimizer pass).
Providers and API keys
Kigi talks to a fixed three-platform registry:
| Platform id | Base URL | Auth |
|---|---|---|
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
(environment wins; values are never logged):
export KIGI_MOONSHOT_API_KEY=sk-... # applies to both open platforms
export KIGI_MOONSHOT_CN_API_KEY=sk-... # platform-scoped, beats the generic name
export KIGI_MOONSHOT_AI_API_KEY=sk-...
# ~/.kigi/config.toml
[platforms.moonshot-cn]
api_key = "sk-..."
[platforms.moonshot-ai]
api_key = "sk-..."
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
(catalog keys are {platform_id}/{model_id}). Models that 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
in config.toml > server-delivered list > built-in fallback.
KIGI_CODE_BASE_URL re-points the subscription platform (useful for
testing); KIGI_MOONSHOT_CN_BASE_URL / KIGI_MOONSHOT_AI_BASE_URL are the
equivalent dev/test overrides for the open platforms.
The web search/fetch tools ride the Kimi Code subscription services and
are present only on OAuth sessions — API-key-only sessions run without
them, matching the official client.
Building from source
rustup toolchain install 1.97.0
cargo build --profile release-dist -p kigi-bin
./target/release-dist/kigi --version
protoc is invoked through the vendored dotslash
launcher at bin/protoc; install dotslash (brew install dotslash or
cargo install dotslash) if it is not already on your PATH.
Coexistence with the official Kimi CLI
Kigi is not affiliated with Moonshot AI or xAI, and it coexists with the
official kimi CLI on the same machine: independent binary name,
independent config directory (~/.kigi), independent keyring credentials
(service kigi), and a KIGI_* environment-variable namespace. Nothing
the official client installs or stores is ever read at runtime or written.
On first launch Kigi offers a one-time, strictly read-only import of
your existing ~/.kimi configuration (MCP servers, custom providers,
default model) via kigi import-kimi — file contents and mtimes under
~/.kimi are left untouched, verified by tests.
Kigi is zero-telemetry: the only outbound connections are the inference/auth APIs you configure, GitHub Releases for updates, and MCP servers you add.
License
Apache-2.0. See LICENSE, NOTICE, and
THIRD-PARTY-NOTICES. Code ported from
openai/codex and sst/opencode is documented in
crates/codegen/kigi-tools/THIRD_PARTY_NOTICES.md.
Kigi is based on Grok Build Open Source; the --version output carries the
attribution.