BitTorrent Creator's New Project Manyana: CRDT Version Control + AI-Powered Dev Workflows
Bram Cohen just dropped Manyana — a fundamentally sound CRDT-based version control system. Here's what it does, why it matters, and how to build AI-powered development workflows on top of it using NexaAPI.
⚡ TL;DR
- • Manyana is a new CRDT-based version control library by Bram Cohen (BitTorrent creator), released March 22, 2026
- • It solves merge conflicts at the data structure level — merges never fail and always converge
- • You can combine it with NexaAPI to build AI-powered code review, conflict summarization, and commit message generation
- • NexaAPI gives you 50+ AI models (GPT, Claude, Gemini, FLUX) via one OpenAI-compatible key — at 1/5 of official pricing
What Is Manyana?
On March 22, 2026, Bram Cohen — the creator of BitTorrent — released Manyana on GitHub. It's a Python library that provides a fundamentally sound basis for version control using CRDTs (Conflict-Free Replicated Data Types).
The core insight: traditional VCS systems like Git approximate merge correctness with heuristics. CRDTs give you commutativity and associativity of merges for free — meaning merge(A, B) always equals merge(B, A), no matter what.
The project quickly trended on GitHub and sparked discussion on Hacker News — because it's not just an academic exercise. Manyana ships a working Python implementation with a clean public API.
Why This Matters for Developers
Consider a classic merge nightmare: two developers branch from the same file. Left deletes a function. Right adds a logging line inside it. Traditional Git gives you opaque conflict markers:
<<<<<<< left
=======
def calculate(x):
a = x * 2
logger.debug(f"a={a}")
b = a + 1
return b
>>>>>>> rightManyana's output tells you exactly what each side did:
<<<<<<< begin deleted left
def calculate(x):
a = x * 2
======= begin added right
logger.debug(f"a={a}")
======= begin deleted left
b = a + 1
return b
>>>>>>> end conflictThis is both more informative and more honest. You can see the structure of the conflict — not just two opaque blobs.
Manyana's Python API
Manyana exposes four core functions. Here's the basic workflow:
# Install: pip install manyana (or clone from GitHub)
from manyana import new_state, update_state, merge_states, make_diff
# Create initial state from file lines
initial_lines = ["def calculate(x):", " a = x * 2", " b = a + 1", " return b"]
base_state = new_state(initial_lines)
# Branch A: delete the function
branch_a = update_state(base_state, []) # empty file
# Branch B: add a logging line
new_lines = ["def calculate(x):", " a = x * 2", " logger.debug(f'a={a}')", " b = a + 1", " return b"]
branch_b = update_state(base_state, new_lines)
# Merge — always succeeds, always converges
merged_state, conflicts = merge_states(branch_a, branch_b)
if conflicts:
print("Conflicts found — human review needed")
print(make_diff(merged_state))
else:
print("Clean merge!")Key properties: merges are commutative (order doesn't matter), associative (grouping doesn't matter), and history-aware (the state captures enough edit history to merge correctly with any branch sharing a common ancestor).
Add AI Superpowers with NexaAPI
Manyana gives you structured conflict data. NexaAPI lets you pipe that data into any AI model — Claude, GPT, Gemini — to generate human-readable conflict summaries, suggest resolutions, or auto-generate commit messages.
NexaAPI is an OpenAI-compatible inference API that aggregates 50+ models at 1/5 of official pricing. You can access it via RapidAPI, PyPI, or npm.
Python: AI Conflict Summarizer
from nexaapi import NexaAPI
from manyana import new_state, update_state, merge_states, make_diff
# Initialize NexaAPI client
client = NexaAPI(api_key='YOUR_API_KEY')
def ai_conflict_summary(diff_output: str) -> str:
"""Use Claude via NexaAPI to summarize a Manyana conflict."""
response = client.chat.completions.create(
model='claude-sonnet-4-6', # ~$0.60/1M tokens via NexaAPI
messages=[
{
'role': 'system',
'content': 'You are a code review assistant. Given a Manyana CRDT merge conflict, explain what happened in plain English and suggest the best resolution.'
},
{
'role': 'user',
'content': f'Here is the merge conflict output from Manyana:\n\n{diff_output}\n\nPlease explain what happened and suggest how to resolve it.'
}
],
max_tokens=500
)
return response.choices[0].message.content
# Example usage
base_state = new_state(["def calculate(x):", " a = x * 2", " b = a + 1", " return b"])
branch_a = update_state(base_state, []) # deleted function
branch_b = update_state(base_state, ["def calculate(x):", " a = x * 2", " logger.debug(f'a={a}')", " b = a + 1", " return b"])
merged, conflicts = merge_states(branch_a, branch_b)
if conflicts:
diff = make_diff(merged)
summary = ai_conflict_summary(diff)
print("🤖 AI Conflict Summary:")
print(summary)JavaScript: AI Commit Message Generator
import NexaAPI from 'nexaapi';
const client = new NexaAPI({ apiKey: 'YOUR_API_KEY' });
async function generateCommitMessage(diffOutput) {
const response = await client.chat.completions.create({
model: 'gpt-5.4-mini', // Fast and cheap: ~$0.15/1M tokens via NexaAPI
messages: [
{
role: 'system',
content: 'Generate a concise, conventional commit message based on the provided code diff.'
},
{
role: 'user',
content: `Generate a commit message for this change:\n\n${diffOutput}`
}
],
max_tokens: 100
});
return response.choices[0].message.content;
}
// Example: auto-generate commit messages for Manyana state updates
const diff = "Added logger.debug line to calculate() function";
const commitMsg = await generateCommitMessage(diff);
console.log(`✅ Suggested commit: ${commitMsg}`);
// Output: "feat(calculate): add debug logging for intermediate value a"3 AI-Powered Dev Workflow Ideas
1. 🔍 Smart Conflict Reviewer
Pipe Manyana's structured conflict output into Claude Sonnet via NexaAPI. Get plain-English explanations of what each branch did and a suggested resolution — before your team even opens the file.
2. 📝 Auto Commit Messages
Use Manyana's diff output + GPT-5.4 mini (via NexaAPI at $0.15/1M tokens) to auto-generate conventional commit messages. Integrate into your CI pipeline for zero-effort commit hygiene.
3. 🤖 Decentralized AI Code Review
Manyana's commutative merges make it ideal for decentralized workflows. Combine with NexaAPI's image generation (FLUX) to auto-generate architecture diagrams from code diffs — no human reviewer needed for routine changes.
NexaAPI Pricing vs Official
| Model | Official Price | NexaAPI Price | Savings |
|---|---|---|---|
| Claude Sonnet 4.6 | $3.00/1M tokens | ~$0.60/1M | 80% off |
| GPT-5.4 mini | $0.75/1M tokens | ~$0.15/1M | 80% off |
| Gemini 2.0 Flash | $0.075/1M tokens | ~$0.015/1M | 80% off |
| FLUX Schnell (image) | $0.003/image | ~$0.001/image | 3x cheaper |
Source: nexa-api.com/pricing | Retrieved March 27, 2026
Get Started in 2 Minutes
# Install Manyana pip install manyana # or: git clone https://github.com/bramcohen/manyana # Install NexaAPI Python SDK pip install nexaapi # Or JavaScript npm install nexaapi
Get your NexaAPI key at nexa-api.com or via RapidAPI. One key, 50+ models, pay as you go.
Build AI Dev Tools on Trending Repos
NexaAPI gives you access to Claude, GPT-5.4, Gemini, and FLUX at 1/5 of official pricing. One OpenAI-compatible API key. No subscriptions.
FAQ
What is Manyana by Bram Cohen?
Manyana is a Python library released by BitTorrent creator Bram Cohen on March 22, 2026. It implements CRDT-based version control, where merges are always conflict-free at the data structure level and always converge to the same result regardless of merge order.
How does Manyana differ from Git?
Git uses heuristics to approximate merge correctness, which breaks down in complex merge histories. Manyana uses CRDTs to guarantee commutativity and associativity of merges — meaning the result is always deterministic and order-independent. It also provides more informative conflict presentations that show exactly what each branch did.
What is NexaAPI?
NexaAPI is an OpenAI-compatible inference API that gives developers access to 50+ AI models — including Claude, GPT-5.4, Gemini, and FLUX — at approximately 1/5 of official pricing. It's available via nexa-api.com, RapidAPI, PyPI (pip install nexaapi), and npm (npm install nexaapi).
Can I use NexaAPI with Manyana for code review automation?
Yes. Manyana's structured diff output is ideal for feeding into LLMs. You can use Claude Sonnet 4.6 via NexaAPI to generate plain-English conflict summaries, auto-generate commit messages with GPT-5.4 mini, or build fully automated code review pipelines — all at 80% below official API pricing.