Browser actions for AI agents that are classified, approved and logged
Runs locally- 1 tool
- Open source
- Browser automation
Browser actions for AI agents that are classified, approved and logged
Runs locallyMCP wrapper that holds database writes until a second person approves them on their phone
Runs locallyLocal code evidence graph and 66 MCP tools for coding agents, offline and native
Runs locallyAudit Google Tag Manager tags, triggers and variables, then version and publish
Runs locallyTransactional refactoring for coding agents: previews, apply gate and rollback
Runs locallyQuery and edit Firestore documents and look up Firebase Auth users from your agent
Runs locallyRead Google Slides decks and speaker notes, add slides and replace text
Runs locallySearch 1,516 line icons by meaning or look and get SVG at any size or weight
Runs locallySelf-hosted work database that agents drive over MCP, in a single SQLite file
Runs locallyShared context and file queues so coding agents on one team stop overwriting each other
Runs locallyDecode MsgPack bytes into readable text, including from paused debugger variables
Runs locallyLocal non-custodial MCP server for swapping USDC on Base into BSV, with spending limits
Runs locallyKeep Jira issues as read-only Markdown files your agent can search, with source links
Runs locallySelf-hosted job application tool: tailored CVs and cover letters for DACH roles
Runs locallyRead-only Trino access for agents, run as the verified user so Trino policy decides
Runs locallyLocal deep research assistant that checks each citation and keeps what it finds
Runs locallyQueue non-urgent LLM tasks and run them in the lowest-carbon grid hour
Runs locallyLet Claude edit, typeset and fix errors in a self-hosted LaTeX project
Not checked yetCreate AI personas, generate short videos and schedule posts to YouTube and Instagram
Not checked yetRead-only FHIR chart tools for MCP, with human-approved writes
Runs locallyAdd animated word-by-word captions to videos from Claude, Cursor or the command line
Runs locally
Rank security scanner findings by exposure, criticality and exploitability
Runs locallyKeep API keys in your OS keychain and give coding agents only what policy allows
Runs locallySelf-hosted MCP memory server with hybrid search and a learning memory graph
Not checked yetSelf-hosted MCP server: shared agent memory, document search and a code index
Not checked yetLet one coding agent hand tasks to other installed agents and get answers back
Runs locallyGoogle Workspace automation with staged writes, bulk plans and undo
Runs locallyRun cross-repository beads work and hive status for agent-driven engineering
Runs locallyLet coding agents read network calls, crashes and logs from a running Android debug app
Runs locallyAsk questions of a Primavera P6 schedule: critical path, DCMA checks and what-if
Runs locally