apache/maka
Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.
About the project
Apache Maka (Incubating) is an agent workspace that keeps a complete append-only RuntimeEvent log of every model message, tool call and permission decision. It ships Desktop, TUI and CLI clients, and you bring your own model (cloud API, local or gateway) with data staying local.
Useful for
- Run a one-shot agent task from the CLI to summarize a repository and flag risks
- Build Desktop from source and wire a local model via Settings → Models
- Recover a crashed session by replaying the RuntimeEvent log instead of losing context
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 40 stars today.
- Interest is fading: the two-day pace is 51% of the previous week and a half.
- GitHub Trending this month: #16, +4,005 stars.
- Top new repositories in the last 4 months: #89.
- About 6 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 5,343
- Stars in a day
- 40
- Forks
- 497
- Issues and pull requests
- 5,200
- Watchers
- 25
- Language
- TypeScript
- License
- Apache-2.0
- Latest release
- v0.2.0-dev.31.20260913 · September 13, 2026
- Created
- May 27, 2026
- Last push
- September 13, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026GitHub Trending this month: #15, +4,005 stars; Top new repositories in the last 4 months: #89
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.