GitNexus (Akon Labs)
The open-source kernel for coding agents
What it does
GitNexus (45k Github stars) is a Knowledge Graph Kernel that unifies every codebase in your org into one source of truth your coding agents can query. It resolves your code into a deterministic graph, so agents get exact callers, imports, and impact instead of embedding guesses, across every repo and SCM you run. On our public benchmark (https://www.akonlabs.com/benchmarks), coding agent runs 51% cheaper with GitNexus connected. It works with any agent over MCP.
GitNexus indexes any codebase into a knowledge graph of every dependency, call chain, cluster, and execution flow, so AI agents never miss code.
A real codebase is tens of thousands of symbols tangled across files, packages, and repos. Agents that grep their way through it miss dependencies, break call chains, and ship blind edits. GitNexus lets the model walk resolved execution flows instead of grepping file after file. On DeepSWE (a single-issue benchmark that can't even exercise multi-repo graphs or impact analysis), reading process-by-process alone fixed 68.4% of issues against 37.0% with no graph, on fewer tokens and fewer steps. The savings are a side effect of reading code the right way. GitNexus parses every file with Tree-sitter and resolves imports, call chains, field types, and return types across the codebase:…from akonlabs.com
Pricing, as stated on its site
Free tier, paid plans from $29/mo — Open source free tier for individual developers; Enterprise managed SaaS at $29/seat/month; self-hosted enterprise option with custom pricing
checked September 2026 · prices change
Does the same job
all alternatives →
Arena Agent Mode with GitHub11d ago · arena.ai · ▲98Get real work done, moving from idea to shipping in minutes
Aura: Agents + Git + Intent Open SourceJul 2026 · ▲174OSS IDE for controlling AI coding agents with built in loops
- FAFreeact – A Lightweight Library for Code-Action Based Agents2025 · github.com · ▲122
Hello! We just released freeact (https://github.com/gradion-ai/freeact), a lightweight agent library that empowers language models to act as autonomous agents through executable code actions. By enabling agents to express their actions directly in code rather than through constrained formats like JSON, freeact provides a flexible and powerful approach to solving complex, open-ended problems that require dynamic solution paths. * Supports dynamic installation and utilization of Python packages at runtime * Agents learn from feedback and store successful code actions as…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com