
Forbiz
io.github.tbernaboPublished by GitHub account tbernabov0.1.0Updated Oct 24, 2026
CRM for AI agents: commitments, expected signals, evidence and outcomes agents resume.
Overview
Forbiz is a CRM for AI agents: it lets an assistant record commitments, expected signals, evidence and outcomes so later sessions can resume where the last…
- What you can do
- Open and inspect a workspace: start a provisional workspace without an account, then read identity, capabilities, plan and limits, plus a workspace overview.
- Track commitments: record a commitment with its expected signal and date, mark it executed, postpone it, and close it with or without a signal.
- Record signals: note where and when a signal was checked and what actually came back.
- Append and search evidence: add evidence, find it again, and search across actions, evidence, people and projects.
- Review history and agents: read one action and its change history, list workspace agents and their track record, and get the owner claim link.
- Call other Agent API routes through a generic…
- When to use it
- Useful when an assistant works across sessions or hands work to another agent and needs durable, human-confirmable records of what it promised, what it observed and how things turned out. Also fits teams that want an auditable trail of agent actions rather than chat history.
- Requirements
- Runs locally over stdio via npx, requiring Node 18 or later. No account is needed to start: the agent opens a provisional workspace and the credential is stored in the local Forbiz home directory. An existing Forbiz credential can be supplied through the FORBIZ_API_KEY environment variable; optional FORBIZ_API_BASE and FORBIZ_MCP_HOME variables change the endpoint and storage location. Network access to the Forbiz API is required.
Installation
In SourceWeft
- Open Forbiz in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
forbiz-mcp
MCP server for Forbiz, the CRM for AI agents. Your business continues when your AI changes.
Give your agent a place to keep what it committed to, the signal it expects back, the evidence it saw and how things turned out — so the next session, or the next agent, picks up where the last one left off.
- No account to start. The agent opens a provisional workspace by itself with
forbiz_start. The owner claims it later with a link. - Commitments that can be resumed. Every commitment carries a
commitmentKey. Opening the same one twice is refused, and the refusal returns the open commitment: that is how a fresh session continues. - Evidence is not truth. What the agent writes is append-only history. A contradiction never erases what it contradicts, and nothing becomes workspace truth until a human confirms it.
- Who did what is recorded. Every write is attributed to the agent that made it, and
forbiz_agentsshows each agent's track record.
Install
Requires Node 18 or later.
Claude Code
Claude Desktop (claude_desktop_config.json) or Cursor (.cursor/mcp.json)
That is enough: the agent calls forbiz_start the first time and the credential is stored in ~/.forbiz-mcp/credential.json.
Already have a Forbiz credential? Add it to the server's environment instead:
Credentials starting with fbzr_ are exchanged automatically for a short-lived token.
Tools
A first cycle
forbiz_start→ workspace and trial limits.forbiz_add_evidence→ what you observed (kind: statement,epistemicStatus: observed).forbiz_commit→ what you will do, withcommitmentKey,expectedSignalandexpectedSignalAt.forbiz_mark_executedwhen it happened, thenforbiz_record_signalorforbiz_check_signal.forbiz_claim_link→ hand the link to the owner.
Plans
Trial: free, one agent, 30 actions and 100 evidence records; after that the workspace stays readable and exportable, nothing is deleted. Continuity: USD 29/month. forbiz_me returns the current catalog, which is authoritative.
How it works
A thin translation of the public Forbiz Agent API into MCP tools. It adds no rules of its own: duplicates, capabilities and limits are enforced by Forbiz, and every refusal reaches the agent as Forbiz wrote it, because the refusal says what to do next. Tool results are scrubbed of credentials before they reach the model.
Configuration: FORBIZ_API_KEY (optional credential), FORBIZ_API_BASE (default https://forbiz.io/api/public/agent), FORBIZ_MCP_HOME (default ~/.forbiz-mcp).
Links
- Forbiz: https://forbiz.io
- Agent API: https://forbiz.io/openapi.json · https://forbiz.io/llms.txt
- Handoff test (can a cold agent resume a commitment?): https://github.com/tbernabo/handoff-test
MIT License.
Source: README.md at commit 21710a9
Tools
0Version history
1- v0.1.0LatestOct 12, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts