Bahulam Code · Coding agent CLI

Ship without restrictions.

Bahulam Code reads your codebase, plans changes, edits files, and self-corrects on failure. No restrictions on tokens, model choice, or how far you take a run — bring your own key, pick any of the 40+ models we route, keep going until the problem is solved.

What is Bahulam Code?

Bahulam Code is Bahulam's coding agent CLI. It reads your codebase, plans changes, edits files, and verifies its own work by running tests — self-correcting on failure instead of stopping at the first error. It supports 40+ models via direct providers or OpenRouter, and it's self-hostable.

Install

One line in your terminal. Then sign in and go.

01 · Install globally

$ npm i -g @bahulam/code

02 · Sign in via browser

$ bahulam login

03 · Run

$ bahulam "fix the bug"

What it does

Sub-agents

Explorer reads. Planner designs. Coder writes. Each sub-agent uses the model that fits its role — a fast model to scan, a reasoning model to plan, a coding model to write. You compose the team; Bahulam Code handles the routing.

Bring your own model

40+ models supported via direct providers or OpenRouter — Anthropic, OpenAI, DeepSeek, GLM, Tencent, Google, and more. Bring your own key, pick the model that fits your budget and quality bar, switch mid-session if you change your mind.

Sandbox execution

Agent work runs in Docker or Firecracker MicroVMs. Nothing touches your host unless you approve it. Six permission modes — from strict approval to full autonomy — let you tune the safety envelope per project.

Cross-session memory

Bahulam Code keeps a project-local .kepler/ folder with tasks, checkpoints, approvals, and durable notes. Resume a session next week and the context is still there. No prompt-stuffing to catch the agent up on what it already knows.

MCP + tool ecosystem

Model Context Protocol servers plug in as first-class tools. GitHub, Notion, Postgres, Sentry, custom services — all reachable from within an agent run without wrapping them yourself.

Self-hostable

No vendor lock-in. Deploy the runtime on your infrastructure, keep your data in your VPC, pin the CLI version. Or use the hosted platform when convenience matters more than isolation.

Benchmarks — public and reproducible

58.7%

SWE-bench Lite

npm CLI · 300 instances

67.8%

SWE-bench Verified

339/500 resolved

94.3%

Prompt cache

flash last-run hit rate

See methodology

Common questions

Read the full FAQ

Can I use my own API keys with Bahulam (BYOK)?

Yes. Every paid plan supports BYOK — bring your own provider key and route requests directly, at 0 platform credits. Pick the model that fits your budget and quality bar, and switch mid-session if you change your mind.

Is Bahulam Code self-hostable?

Yes. There's no vendor lock-in — deploy the Bahulam Code runtime on your own infrastructure, keep your data in your VPC, and pin the CLI version. Use the hosted platform instead when convenience matters more than isolation.

What models does Bahulam Code support?

Bahulam Code routes to 40+ models via direct providers or OpenRouter, including Anthropic, OpenAI, DeepSeek, GLM, Tencent, and Google. Sub-agents can each use a different model — a fast model to scan, a reasoning model to plan, a coding model to write.

Developer resources

docs.bahulam.ai is where Bahulam's engineers ship — API docs, MCP server reference, benchmark artefacts, engineering blog, and the cloud dev environment when it's production-ready.

Bahulam Code is precision at the byte level: read your codebase, plan the change, edit the right files, verify with tests. If you write agents, live there.

Ship your first change today.

Install in a minute. Sign in with a browser. Ship your first change — no rate limits, no gated models, no per-feature metering.