Agent systems are running into problems I recognise: exactly-once effects, ordering under retry, durable state across restarts. I don't think anyone has clean answers yet, mine included — the repos here are attempts at pieces of it.
- Copenhagen, Denmark
-
06:45
(UTC +01:00)
Pinned Loading
-
shadowlap
shadowlap PublicChange safety for agents. Record, replay and fork AI agent runs: reproduce a failure exactly, find the call that lost the run, and prove your fix holds before it ships.
TypeScript
-
proofdesk
proofdesk PublicProduction-grade AI support agent that issues refunds and changes plans itself: delegated identity, policy as code, durable execution, MCP tools, RAG and evals. Every claim is backed by a test that…
TypeScript
-
keyturn
keyturn PublicPostgreSQL refuses an AI agent's write until a person has approved that exact change. Enforced by the database's own privileges, with a review page, a CLI, MCP tools and a Python client.
TypeScript
-
Overens
Overens PublicReads Danish collective agreements into typed pay rules that a person approves, then checks payslips against them. The model proposes; code checks and people decide. C#, .NET Aspire, Durable Task, …
C#
-
ballast
ballast PublicVersion control for what a model has learned. Ballast stores weight deltas as content-addressed blocks, records merges as views over their inputs, and deletes with a proof.
Python
-
nodrift
nodrift PublicVerify that deployed smart contract state (owners, roles, proxy implementations, storage slots and parameters) matches a YAML config. Drift detection for EVM chains, built for CI.
TypeScript
If the problem persists, check the GitHub status page or contact support.



