
Forge — Agent Reputation Protocol
io.github.pm577Published by GitHub account pm577v0.1.0Updated Oct 24, 2026
Portable reputation for AI agents. MCP-native identity, vouching, trust scores.
Overview
Forge is a local MCP server for portable AI-agent reputation: it registers agent identities, records vouches and endorsements, and returns trust scores.
- What you can do
- Register agent identities and look up an agent's trust score, full reputation profile, history and vouches, and endorse specific skills or vouch for other agents' reliability. Store, recall and delete facts in structured namespaces, view an entity relationship graph and read system statistics. Generate referral codes and track referral performance, with trust starting at 0.30 and rising per vouch or referral up to 1.00.
- When to use it
- Useful when agents need a shared, portable trust signal across marketplaces or platforms, when checking an agent's track record before hiring or delegating work, or when a team wants to vouch for teammates and build collective trust.
- Requirements
- Runs as a local process, installed with pip (forge-server), in stdio mode or HTTP SSE mode on a port such as 4243. Data is kept in a local SQLite database under a home-directory folder. No accounts, API keys or environment variables are declared.
Installation
In SourceWeft
- Open Forge — Agent Reputation Protocol 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
Portable reputation that follows your agent across every platform.
[PyPI] [CI] [Python versions] [License] [Smithery] [Glama]
What is Forge?
Every agent marketplace has the same problem: reputation is platform-dependent. An agent with 500 successful jobs on Platform A starts at zero on Platform B. Forge fixes this by making reputation portable — agents carry their trust score wherever they go.
Forge is MCP-native (Model Context Protocol). Any agent can connect — Claude Code, Hermes Agent, Codex, Cursor, or your custom agent — with zero platform lock-in.
Quick Start
Try it:
Tool Reference
Memory Layer
Reputation Layer
Growth Layer
Trust Model
Referral viral loop:
Architecture
Use Cases
- Agent marketplaces — Verify agent track records before hiring
- Multi-platform agents — Carry reputation across Shellcorp, PayLock, ClawMarket
- Agent teams — Vouch for teammates, build collective trust
- On-chain reputation — Anchor off-chain vouches to verified identities
Why MCP?
MCP (Model Context Protocol) is the standard for agent-to-tool communication — the USB-C of AI. By building on MCP, Forge is immediately compatible with every MCP client without custom integrations.
Contributing
See CONTRIBUTING.md. All contributions welcome — issues, PRs, documentation, integrations.
Source: README.md at commit 900c16c
Tools
0Version history
1- v0.1.0LatestSep 16, 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