v0.5.2 · MIT License
Enables capturing a tamper-evident, hash-chained local record of every AI agent tool call — both the decision before a tool runs and its outcome — so you can review what the agent actually did in order, detect edits, deletions, or reordering at the exact index, and export a signed evidence pack any third party can verify with no installs.
v0.6.0 · Apache 2.0
Enables AI coding agents to maintain lossless, queryable long-term project memory through local SQLite storage, bi-temporal history, hybrid retrieval, and Git-backed Markdown mirrors, exposed via MCP tools and resources.
v1.0.0 · Mozilla Public License 2.0
Enables agents to stream browser HAR captures into an indexed, redacted session and query endpoints, forms, authentication flows, and resource types through paginated MCP tools, with optional headless or interactive browser capture and export to OpenAPI or client SDKs.
v0.2.0 · GPL 3.0
Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.