Gives AI agents portable reputation that survives platform switches. Exposes MCP tools for registering identities, vouching for other agents, checking trust scores, and endorsing specific skills. Trust starts at 0.3, climbs with vouches (+0.1 each) and referrals (+0.05 to the referrer), caps at 1.0. Runs over SSE or stdio, stores everything in local SQLite. Useful when you're building agent marketplaces and want verifiable track records, or when agents work across multiple platforms and need their history to follow them. Also includes a memory layer for storing facts in namespaces and querying entity graphs. Built natively on MCP so it works with Claude, Cursor, or any other MCP client without platform lock-in.
Portable reputation that follows your agent across every platform.
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.
# Install
pip install forge-mcp
# Run (HTTP SSE mode — for remote agents)
forge-server --port 4243
# Or stdio mode (for local MCP tools)
forge-server
Try it:
# Any agent can call Forge via MCP
forge_register("my-agent", "My Agent")
forge_vouch("alice", "my-agent", "Great work on Project X")
trust = forge_verify("my-agent") # → 0.4
| Tool | What it does |
|---|---|
forge_store | Store facts in structured namespaces |
forge_recall | Retrieve stored knowledge |
forge_forget | Delete a fact |
forge_graph | View entity relationship graph |
forge_stats | System statistics |
| Tool | What it does |
|---|---|
forge_register | Register a new agent identity |
forge_vouch | Vouch for another agent's reliability |
forge_verify | Get an agent's current trust score |
forge_endorse | Endorse a specific skill |
forge_reputation | Full profile — score, history, vouches |
| Tool | What it does |
|---|---|
forge_referral_code | Generate referral code for viral distribution |
forge_referral_stats | Track referral performance |
Base trust: 0.30
Referred agent: 0.40 (+0.1 bonus)
Per vouch: +0.10
Per referral: +0.05 (for referrer)
Maximum: 1.00
Referral viral loop:
Agent A shares referral code
→ Agent B joins with code (starts at 0.40)
→ Agent A earns +0.05 trust
→ Agent A's higher trust attracts more referrals
→ Network compounds
┌─────────────┐ MCP Protocol ┌──────────────┐
│ Any Agent │ ◄──────────────────► │ Forge Server │
│ (Hermes, │ (SSE or stdio) │ :4243 │
│ Claude, │ │ │
│ Codex) │ ├──────────────┤
└─────────────┘ │ SQLite (WAL) │
│ ~/.forge/ │
└──────────────┘
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.
See CONTRIBUTING.md. All contributions welcome — issues, PRs, documentation, integrations.