- Context Foundry @context-foundry/context-foundryRecursive Claude spawning for autonomous project builds with self-healing test loops8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- Knowing @blackwell-systems/knowingContent-addressed code graph with 22 MCP tools for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- DOS — the trust substrate for agent fleets @anthony-chaudhary/dos-kernelVerify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- Memory Journal @smithery/neverinfamous-memory-journal-mcpA MCP server built for developers enabling Git based project management with project and personal…16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.20 GitHub stars.
- Maple @maple-kit/mapleReview comments pinned to a running frontend, read and resolved by your coding agent.Not assessed yet.Runs on your machine, installed from npm.19 GitHub stars.
- adrkit decision memory @adrkit/mcpDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Ekbasis @openinterpretability/ekbasisForesee what git commands and multi-step changes will do, as calibrated probabilities3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.18 GitHub stars.
- GitWarren @klarluft/gitwarrenCode review on your own machine, for you and your coding agent. Nothing leaves your computer.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- uploads.sh @uploads/mcpHost files from coding agents; stage on a branch and attach to GitHub PRs.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.18 GitHub stars.
- CommitLore @monglong0214/commitloreGit-native decision memory for coding agents: only the decisions still in force for the edited path5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.18 GitHub stars.
- OrangePro @orangepro/mcpFind test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Agentpack @ihorponom/agentpackRepo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Cortex @danielblomma/cortexLocal repo context for coding assistants with semantic search and graph relationships.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- CALM @eilodon/calm-mcpMCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
- CodeWiki MCP — AI-generated docs for GitHub repos @izzzzzi/codewiki-mcpMCP server for codewiki.google: search repos, fetch wiki docs, ask questions6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
- GraphPilot @graphpilot-oss/graphpilotStructural memory for coding agents: callers, callees, blast radius and symbols over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
- Oss Autopilot @costajohnt/oss-autopilotOpen source contribution manager with PR tracking, issue discovery, and CI diagnosis4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
- Unblocked @getunblocked/unblocked-mcpUnblocked is the context layer for agentic software development.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.16 GitHub stars.
- NexusMem @yaminbkk/nexusmemLocal-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Docdex @bekirdag/docdexFast per-repo documentation indexer and full-text search MCP server for codebases.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Myc @aistastudio/mycTask queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Girder @dhishwasher/girderSaves AI coding-agent context by giving exact code instead of whole files, from a local graph.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Orbit @constellation-works/orbitOrbit's local-first task and workflow registry for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Koragraph @koragraph/koragraphLocal multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
