agentic-prover/aprover

Forall (∀) is a coding harness from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs.

Specs first. Code second. Proof always. You define the what. LLMs generate the how. hlv validates the proof.

Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with generated invariants in a Docker sandbox, and returns PROVEN / REFUTED / UNVERIFIED with a JSON certificate. Part of a verifier-gated, multi-model agent runtime.

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

Specula: An agentic tool for finding deep bugs in system code using TLA+

An SDK for verifiable intent, inline with code: one-line claims above your functions, verified at the rigor you choose and flagged when they drift. Agent-first, MIT.

Research prototype tool for modular formal verification of C, Rust and Java programs

Adversarial bug-hunting code review for AI agents. 3 parallel subagents attack code from different angles, then a consolidator merges and triages findings. Read-only — finds problems, doesn't fix.