I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half... the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:show more

Pro tip boss: don’t promote your own shit praising yourself in the third person. Immediately makes me not trust it. Let someone else sing your praises

okay man, but i think the algo loves this format so i was forced to

@jeffscottward Ok yeah it's cringe but if the ideas are good enough and it's not a routine marketing bait then I'll forgive it

@jeffscottward <3

So basically llm-tldr

context+ does not contain only semantic search llm tldr is a cool project though

Keep hustling man. I have huge respect for people that ship useful code 🙏🏽

appreciate it man

Nice website 👌

oh no the phone ui sucks im gonna fix it

Yes please do...

i actually fixed the same issue before it came back again

Oho, not a problem, thanks for following, means a lot.

<3

you made this right? why is this post written like ur reviewing someone else's work 😭

thats a classic post format 😭

oh... am not up to date on engagement methods...

check the repo pya dont worry about the tweet,,,,

thank u for ur work forloop <3

context bloat is the silent killer of agent productivity. you're paying for tokens the model doesn't need, getting worse outputs because of noise, and wondering why your agent went off the rails. 6.5k fewer tokens per task compounds fast across hundreds of runs.

exactly

This is exactly what the ecosystem needs. Context management is one of the biggest bottlenecks in agentic workflows right now. Great to see an open-source solution.

looking for more prs and issues on the repo, thanks

the token savings are cool but I'm more interested in how the semantic search actually works under the hood. is it embedding the AST or just chunking raw source? because those give very different results when you're trying to trace call chains across files

currently the semantic search generates embeddings of each file and ranks the closest files and parts of code depending on how close it is to the query, might work out on caching and deeper search

holy self glaze

I could not find this before so I was building the same thing, thankfully you tricked the algo.

how are u gonna use it

Have agents build visual flows for current vs future state of code to aid architecture and code review work for a very very large codebase.

context bloat is a major efficiency killer, anything that reduces token usage and speeds up task completion is a step in the right direction.

+1

Cocoindex does the same?

omg how many are there

6.5k tokens saved per issue adds up fast, been looking for something like this for bigger codebases

i am constantly improving this and i think we can achieve even higher differences

That must be insane

isnt it!!

Trust me bro

yes i do

I made something similar this week.

show

Still deciding on whether to open source or not. n.b.: all-MiniLM will be swapped for something faster and better

I'm working on a VM for coding agents at the moment. This one will definitely be open-sourced.

deyum u okay if i rt?

sure. would you also give me a follow back. I'm sure we can exchange ideas and maybe collaborate.

Yoink

wdyt lucid!?

im stealing the Content-hash embedding cache concept owo saves extra tokens on calls with it, goated we essentially have a similar way with the memory and its hybrid scoring tho which I find very interesting xD

its gonna bang ngl

thank youuuuu <3

Did the same but for Claude Code:

Nice find, thanks!

its me lol

Is the same as using Serena?

theres more than semantic code search but yeah somewhat like that context+ has blast radius, undo trees, and even structural file trees

context management is quietly the biggest unlock for agentic coding right now. the difference between burning tokens guessing and actually understanding the codebase is everything. huge move open sourcing this

Pretty cool. What about accuracy?

idk, didnt measure the real numbers yet, but i'm pretty sure they are higher since i have been using this as a skill and it worked way better

And by 'this guy' did you mean yourself?

cursor does a lot of that stuff, read up their blogs. also, modern tools doesn’t guarantee efficacy; claude code uses just grep! i like the ideas but if there are no benchmarks on the efficacy of the results you claim then a bit hard to trust!

Fewer tokens matters, but higher retrieval precision is the real win, because agents fail when context is full of plausible but irrelevant code. Tracking wrong file picks and rollback rate would make the benchmark even stronger.tronger.

how does this compare to Serena?

At its core this seems familiar to tools like colgrep. How do you choose one or the other?

6.5k fewer tokens sounds great, but context bloat usually comes back once real codebases get involved. Has anyone tested this on a project bigger than a demo?

would love to hear feedback from more uses and will improve context+ more over time

bro is so cracked

>the agent using this tool used ~6.5k fewer tokens This is completely irrelevant noise bruh

> this guy You’re this guy. Make me want to not even click

Isn't this basically what cursor is doing?

never used cursor though, does it actually do that? i dont think so, it doesnt generate embeddings for semantic search

Cursor has non-stopped cooked. I primarily use CodexCLI, but Cursor has a great product. Semantic (vectorized) search has been a big feature of Cursor for a while.

goddam

I saw a post last month about using the JetBrains PSI to reduce token use by 90%, so I made a plugin that does only this. For non-JB languages, I call ripgrep on Read for function signatures or MD headings. Your MCP is definitely more polished though!

Aha! "Context tree" is the name for the ideas that have been banging around in my head for almost a year now! I love it!

highly fw em

The compaction loop angle is real. I had my AI chief of staff basically seize up from context bloat last week - 184MB embedding cache with no TTL, 49 orphaned sessions, wrong SQLite journal mode. Four problems stacked on each other. Wrote up the full breakdown + fix here if anyone's dealing with something similar:

Why do I have to use ollama?

🔥🔥🔥