{
  "schema_version": "1.1",
  "id": "archive:https://github.com/apache/maka",
  "slug": "maka-01vaj44",
  "url": "https://feed7.dev/p/maka-01vaj44",
  "title": "apache/maka",
  "why_included": "Maka gives local coding-agent runs a durable event log, sandbox boundary, recovery path, and shared runtime across desktop, CLI, and evals. It is early, source-only software with changing interfaces.",
  "summary": "Apache Maka records model messages, tool calls, results, permission decisions, and termination events in an **append-only local log**. Desktop, CLI, TUI, and evaluations execute through one **Runtime Host**, with sandbox approval for file writes and shell commands.",
  "practical_implication": "Builders can treat prompts as projections of durable run history: trim old tool output from context without deleting evidence, inspect failures, recover crashes, and compare reproducible experiment cells. Its graph mode also uses isolated Git worktrees for parallel implementation.",
  "agent_context": "Apache Maka records model messages, tool calls, results, permission decisions, and termination events in an **append-only local log**. Desktop, CLI, TUI, and evaluations execute through one **Runtime Host**, with sandbox approval for file writes and shell commands.\n\nBuilders can treat prompts as projections of durable run history: trim old tool output from context without deleting evidence, inspect failures, recover crashes, and compare reproducible experiment cells. Its graph mode also uses isolated Git worktrees for parallel implementation.\n\nThis is an **Apache Incubator** project with no approved Apache release. The desktop build currently supports **Apple Silicon macOS**; formats and commands may change, Windows is an unsigned preview, and secrets remain plaintext to the local OS account.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/apache/maka",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "harness-engineering",
    "agent-reliability",
    "sandboxing"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "This is an **Apache Incubator** project with no approved Apache release. The desktop build currently supports **Apple Silicon macOS**; formats and commands may change, Windows is an unsigned preview, and secrets remain plaintext to the local OS account."
  ],
  "connected_context": {
    "meaning": "Maka turns several proposed reliability primitives into one local runtime: durable event history, permissioned execution, replayable evaluations, crash recovery, and isolated parallel work. It strengthens the case for event-sourced harnesses while narrowing immediate adoption through incubator status, changing interfaces, limited platform support, and plaintext local secrets.",
    "corpus_size": 551,
    "generated_at": "2026-08-24T10:04:40.300Z",
    "connections": [
      {
        "title": "Agent Frameworks Considered Harmful — Rémi Louf, .txt",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=KHudyx5wW3U",
        "feed7_url": "https://feed7.dev/p/agent-frameworks-considered-harmful-remi-louf-txt-1ku9s0h",
        "reason": "Maka directly implements the candidate’s durable-event and replay architecture through an append-only log shared across interfaces and evaluations."
      },
      {
        "title": "Multiplayer agentic engineering — Arjun Singh, Superconductor",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=OL7kfezynJM",
        "feed7_url": "https://feed7.dev/p/multiplayer-agentic-engineering-arjun-singh-superconductor-01w4k91",
        "reason": "Its Runtime Host, sandbox approvals, visible history, and isolated Git worktrees provide a local implementation of the candidate’s inspectable, isolated parallel-agent workflow."
      },
      {
        "title": "FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsoft",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=GJX19pNhmSw",
        "feed7_url": "https://feed7.dev/p/finops-for-ai-agents-who-spent-all-the-tokens-tisha-chawla-susheem-koul-0artw9n",
        "reason": "Keeping evidence while trimming old tool output separates audit history from active context, supporting run-level context control without deleting the data needed for cost and failure analysis."
      },
      {
        "title": "Building a software factory for AI SDK",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/building-a-software-factory-for-ai-sdk",
        "feed7_url": "https://feed7.dev/p/building-a-software-factory-for-ai-sdk-0udhuk3",
        "reason": "Maka supplies runtime primitives for the factory pattern—isolated worktrees, recorded evidence, and permission gates—while leaving human review and merge authority outside the runtime."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/maka-01vaj44",
    "json": "https://feed7.dev/p/maka-01vaj44.json",
    "markdown": "https://feed7.dev/p/maka-01vaj44.md"
  }
}