Purfle
Visit github.com/clarksonr/purfle
An AI agent identity and trust platform, C#, with signed manifests, capability enforcement and sandboxed execution.
Purfle136
- 20262 weeks logged136
- W1430 Mar128commits
Purfle
Building the loop that refuses to load a tampered agent
- Wrote the manifest identity spec and the trust loop around it: JSON Schema, RFC 0001 on JWS/ES256, a ManifestLoader, and live signature verification against the Azure key registry, complete with tamper detection.
- Built the scheduler and sandbox that enforce what a manifest declares: five trigger types (interval, cron, startup, window, event), a sandbox fix that blocks and logs an out-of-bounds write, crash isolation between agents, and backoff on LLM timeouts and 429s.
- Wired five LLM adapters, Anthropic, Gemini, OpenClaw, Ollama and a built-in tool executor, each reporting token usage, then tested that usage all the way from the adapter through the agent runner into the run log.
- W1323 Mar8commits
Purfle
Scaffolding the manifest schema and the CLI
- Wired Ajv into purfle/core and aligned the root JSON Schema with the spec, so a manifest with a missing or malformed field fails validation before anything tries to load it.
- Wrote the CLI commands, fixed module resolution in purfle/core, then added CLI tests that check init scaffolding validates cleanly against Ajv.
- Added the first tests for identity and schema validation in purfle/core, ahead of any code that would depend on them passing.