PAGES
← all tools
◆ AI Agent Frameworks

maka

0.1.11 open-source

Free plan: not checked yet · Open source: yes

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

What you can do now

Checking Plays…

Summary

Maka is an open-source agent workspace that records every model message, tool call, and permission decision as an append-only log for task execution and recovery. It is licensed under the Apache License, Version 2.0, and functions as a desktop application. It is designed for practitioners who build and test automated workflows, and its documentation positions it alongside other agent harnessesagent harnessesThe software around an AI agent that manages its tools, execution loop, state and limits. It determines how the model's proposed actions are run and checked.. The project has seen steady activity with recent repository updates.

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

How maka helps

Which model messages, tool calls, and permission decisions does the system record for a task run?

records them all in an append-only log

What is the scope of recorded activity during a task execution?

records every model message, tool call, and permission decision

How is the execution record kept for future use?

the log is append-only for task execution and recovery

What components are foundational to the agent workspace?

the Runtime, Evaluation kernel, and various evidence classes

What is the primary output of running the system?

a full per-task record

all 12 features, with the evidence for each →

Languages

Chinese (Simplified) Documentation: Chinese (Simplified)

Features

12 capabilities

Built from maka's releases, docs, README and our own runs. “Seen” marks the month we first spotted a release the vendor didn't date. Group names and tags are our labels.

Compare with peers →

  • maka covers 1 of the 6 ai evaluation and governance capabilities we track.

What maka offers you

  • Command-line interface2
  • Administrative audit log1
  • CI/CD pipeline integration1
  • Disaster recovery1
All capabilities 12 capabilities
Agent workspace audit log shipped Records every model message, tool call, and permission decision as an append-only log to support task execution tracking and recovery. 4 releases · 1 other source · first seen Jul 2026

Shared capability: LLM application tracing

Also counts toward: Administrative audit log

release

  • Adds MAKA_CONTEXT_ACTIVE_TOOL_RESULT_MIN_STEP_NUMBER environment variable to control the step number at which active pruning begins. 0.1.2 · Jul 2026 · source · release history
  • Introduces internal AgentRun ledger and file-backed AgentRunStore for durable trace writes, expanding runtime kernel architecture beyond implicit session management. 0.1.2 · Jul 2026 · source · release history
  • Adds MAKA_CONTEXT_ACTIVE_TOOL_RESULT_MAX_ESTIMATED_TOKENS configuration knob to tune the token threshold for archiving large tool results (default 2048). 0.1.2 · Jul 2026 · source · release history
  • Adds MAKA_CONTEXT_ACTIVE_TOOL_RESULT_PRUNE=off environment variable to opt out of the new default active tool-result pruning behavior in both desktop and headless modes. 0.1.2 · Jul 2026 · source · release history

docs

  • Agent workspace that records every model message, tool call, and permission decision as an append-only log for task execution and recovery.
Session diagnostics collection shipped Guides users through collecting diagnostic information from a Desktop session to help troubleshoot conversation problems. 1 release · 2 other sources · first seen Aug 2026

release

  • Adds opencode-free as a zero-credential default provider 0.1.3 · Aug 2026 · source · release history

docs

  • - [Collect evidence for a Desktop conversation problem](./session-diagnostics.md) ([中文](./session-diagnostics.zh-CN.md)) seen Oct 2026 · source

example

  • Execute Computer Use tasks using the new dedicated executor binary. maka-cu --target <task_description> 0.1.4 · Aug 2026 · source
Branch conversation management shipped Enables branching side conversations to explore alternatives while preserving main thread context. 1 release · 1 other source · first seen Aug 2026

release

  • Adds Codex-style side conversations to branch off a thread and return with the answer 0.1.8 · Aug 2026 · source · release history

example

  • Branch a side conversation to explore an alternative approach without losing the main thread context. In the chat panel, use the side-thread option to start a new branch from the current context. 0.1.8 · Aug 2026 · source
Custom pet appearance system shipped Supports importing, managing, and persisting custom visual assets for the agent's interface. 1 release · 1 other source · first seen Aug 2026

release

  • Enables custom pets with pack import, library management, persistence, and animation 0.1.8 · Aug 2026 · source · release history

example

  • Import a custom pet pack to personalize your assistant's appearance. Go to Settings > Pets, then use the 'Import Pack' button to load your saved pet data. 0.1.8 · Aug 2026 · source
CLI task execution shipped Allows direct session and command execution from the terminal or CI pipelines. 1 release · 1 other source · first seen Aug 2026

Also counts toward: CI/CD pipeline integration, Command-line interface

release

example

  • Execute a Maka session directly from the terminal or CI pipeline. maka run 0.1.7 · Aug 2026 · source
Web search integration shipped suggested Provides a unified web search capability with provider-native routing and citation metadata. 2 releases · first seen Aug 2026

Suggested capability: Retrieval-augmented generation. This is our guess, not confirmed.

Also counts toward: Command-line interface

release

  • Adds a runtime WebFetch tool for agent capabilities. 0.1.7 · Aug 2026 · source · release history
  • Added provider-native web search: one WebSearch routing layer that selects the current model provider or explicit Tavily execution, with OpenAI and Anthropic implementations, durable replay, citation metadata, and privacy-mode coverage across Desktop, CLI, Runtime Host, and opt-in Headless Harbor 0.1.5 · Aug 2026 · source · release history
Version-controlled task execution shipped Manages Git workspaces and file changes with verified runtime integrity for reproducible agent tasks. 2 releases · first seen Aug 2026

release

  • Bundled a hermetic Git runtime and gated managed workspace reads behind owner-bound Runtime Host execution 0.1.6 · Aug 2026 · source · release history
  • Adds managed Git workspaces for version-controlled task execution 0.1.3 · Aug 2026 · source · release history
Managed workspace persistence shipped Maintains agent state and conversation history using local SQLite memory and verified backups. 2 releases · first seen Aug 2026

Also counts toward: Disaster recovery

release

Bounded long-term memory shipped Extracts and stores persistent agent memory for continuity across sessions. 1 release · first seen Aug 2026

release

  • Adds bounded long-term memory extraction for agent sessions. 0.1.7 · Aug 2026 · source · release history
Extended agent concurrency shipped Supports multiple concurrent subagent executions to increase task throughput. 1 release · first seen Aug 2026

release

  • Extended agent swarm concurrency to support 32 concurrent ways via the tool's internal limits. 0.1.4 · Aug 2026 · source · release history
Cost tracking shipped suggested Provides metering of model calls to allow cost estimation for agent operations. 1 release · first seen Aug 2026

Suggested capability: LLM application tracing. This is our guess, not confirmed.

release

Goal event wait coordination documented Provides a mechanism for consumers to wait on goal events, enabling synchronisation across agent tasks or subagents. 1 other source

docs

  • - [Goal event wait consumers](./goal-event-wait-consumers.md) ([中文](./goal-event-wait-consumers.zh-CN.md)) seen Oct 2026 · source

Lines in monospace are the tool's own words: help text parsed from its source, or an endpoint from its API document. Under release, a line is our summary of a dated release. Under docs, it is quoted from the tool's own documentation or website. Each links back to the source it came from.

Score card

  1. Shipping velocity releases a month, last 12 months
  2. Documentation quality release-notes rubric, 0–100
  3. Breaking-change discipline how rarely a release breaks users, and notice given
  4. Maintenance risk quiet time against its own cadence, maintainers
  5. Innovation & surface new capabilities, API and MCP surface
  6. Community health
  7. Contributor trend distinct committers, this year against last
  8. Maintainer concentration bus factor now against a year ago
  9. Issue backlog trend issues closed per issue opened, 12 months
  10. Responsiveness median time to a maintainer’s first reply

Nine scores for maka, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.

Score cards are part of every paid plan.

See plans →

Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.

How this is scored
  • Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
  • Documentation quality — the release-notes rubric published on the analytics page, unchanged.
  • Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
  • Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
  • Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
  • Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
  • Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
  • Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.

Release-note detail over time

See how much detail maka puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.

Checking release-note history…

Explore the full chart →

Releases

Show

10 entries

  1. August 20269
  2. July 20261
    Show

    10 entries

    Project health

    Issue, contributor and maintainer activity in apache/maka, 2023-12 – 2026-11, as of 2026-11-03. Twelve-month figures first; the trend lines run the whole window.

    1. Contributors 155 +155 vs prior 12 months
    2. Maintainers 10 +10 joined · −0 left, last 12 months
    3. Bus factor 2 committers behind half the commits
    4. Community-filed 74% of issues opened, last 12 months
    5. Median time to close 1.2 days first maintainer reply 20 hours
    6. Open backlog 278 of 1,592 issues ever filed
    1. Issues opened / month 119 · 33 communitymaintainers
    2. Open backlog 278
    3. Contributors / month 0
    4. Commits / month 0
    5. Stars not measured
    Issue themes, last 12 months
    • bugs 26%
    • features 28%
    • questions 0%
    • docs 1%
    • other 45%

    Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this

    Libraries its release ships

    What its latest release locks, checked against known advisories.

    None of its release's images build from a lockfile we can read.

    Add the badge to your README

    Maintain this project? The badge links readers straight to this page, so they can follow every release here.

    Tracked by Cyber Toolchain Choose a badge style and copy the code →
    Saved in this browser. Sign in to sync your tools.