Freebuff
BetaOpen-source terminal coding agent that coordinates sub-agents. Formerly Codebuff.
Open-source terminal AI coding agent that coordinates specialized sub-agents to make precise multi-file edits from natural language, renamed from Codebuff to Freebuff and now spanning a CLI, a desktop app, a browser surface and GitHub. Its own published evals report 61% vs 53% against Claude Code over 175+ tasks — their number, not ours. Attaches over the SDK pattern.
- Category
- Coding agents
- Runtime
- Node.js / TypeScript
- Pattern
- SDK / Library
- Adapter package
- @intramedial/actor-codebuff
Status
Freebuff is Beta.
The integration path is built and tested. Customers can attach now; expect minor breaking changes until the 1.0 contract freeze.
Ships from the repo as `@intramedial/actor-codebuff` — not yet on a package registry.
How to attach
SDK / Library.
Install the adapter
Add @intramedial/actor-codebuff to your project.
Issue a workspace API key
Generate a key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
Record each run
Construct the adapter once with your token and workspace id where you initialise your Freebuff agent, then call recordRun(run) when a run finishes. The adapter maps the run to signed receipts and, by default, captures a failed attestation instead of crashing your agent.
Verify
Trigger one agent run. The Witness page shows the record once the agent has emitted it.
What gets recorded
2 event types, captured today.
- agent.invocation
- Every top-level agent run — the input, the resolved output, timing and token usage.
- tool.call
- Each tool or function the agent invokes, with its arguments and returned result.
Same category
Others in Coding agents.
- Claude CodeBeta
Anthropic's terminal-native coding agent. Deepest MCP integration in the category.
- CursorBeta
The default IDE-anchored coding agent. ~800K MAU, $1.2B ARR.
- GitHub CopilotBeta
15M+ users — the most-deployed AI coding tool overall.
- WindsurfBeta
Cognition-owned IDE (post-Cognition acquisition). Cursor's closest competitor.
- DevinBeta
Cognition's autonomous coding agent. Sandboxed cloud environment.
- ClineBeta
Open-source coding agent. 5M+ VS Code installs. BYO-model.
Start recording Freebuff agents.
Every Freebuff run lands in the same canonical Witness record as every other framework in the catalogue: signed, replayable, and exportable as evidence.
A Trustvice ProductAgents act when the plane says yes, and the record says why.
Put admission in front of your MCP servers, repositories, SaaS tools and cloud accounts. Every agent gets a lease or a reason – and you keep the lever to stop any of them.
