Ross ROSS = Recommend OSS · open-source software intelligence for agents

apache/maka

Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did. observed · 2026-10-21

github.com/apache/maka · TypeScript · Apache-2.0 (permissive) observed · 2026-10-21

Health v2 · maintenance only

78/100

  • Activity 100
  • Release rhythm 90
  • Longevity 10

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-22. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 147
  • days_rel: 64
  • days_push: 1
  • n_releases_24m: 12

Full methodology

Adoption not part of the score

5861 stars · 560 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Apache Maka (Incubating) is a local-first AI agent workspace that runs agents on your machine through a single Runtime Host, executing tools under a sandbox boundary. It records model messages, tool calls, tool results, permission decisions, and termination events as an append-only, recoverable execution log.

Use cases

  • run AI agents locally on my machine with sandboxed tool execution
  • audit and replay agent tool calls and permission decisions
  • keep an append-only event log of LLM agent sessions
  • inspect projects with an AI agent without sending data to the cloud
  • manage agent tool permissions in a desktop workspace
  • recover agent execution history from an event-sourced log

When to choose

  • you want a local-first agent runtime with full auditability of every model message and tool call
  • you need sandboxed tool execution with explicit permission decisions recorded as events
  • you prefer a desktop (macOS/Electron) agent workspace plus CLI over cloud-hosted agent platforms

When to avoid

  • you need Linux support, which is not yet available
  • you require a production-stable, graduation-complete Apache project
  • you want a fully managed cloud agent service rather than a local runtime

Facets

application · maturity experimental

agent-framework llm-inference cli developer-tools logging large-language-models developer-tools windows cli local-first event-sourcing sandboxed-tool-execution agent-workspace apache-incubator tool-use audit-log ai-agents automation macos electron desktop typescript

1 source

Member repositories

RepositoryRoleHealth v2
apache/makamain78

For agents

markdown · JSON · MCP: product_card(name="apache/maka")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem