Pinned
Introducing Chroma Context-1, a 20B parameter search agent.
> pushes the pareto frontier of agentic search
> order of magnitude faster
> order of magnitude cheaper
> Apache 2.0, open-source
00:00
Chroma
649 posts
Chroma
@trychroma
Data infrastructure for AI
Apache 2.0
Joined March 2022
- Introducing our latest technical report: Context Rot - How Increasing Input Tokens Impacts LLM Performance Our results reveal that models do not use their context uniformly. full report in replies
00:00 - Introducing Chroma Cloud: an open-source serverless search database that is fast, cost-effective, scalable, and reliable.
00:00 - Chroma is now 4x faster, powered by Rust.
- We introduce representative generative benchmarking—custom eval sets built from your own data that reflect real user queries. thank you @wandb for collaborating! link to report in replies
00:00 - Introducing Chroma Package Search Enable your AI agents to search the source code of your package dependencies Includes 3 MCP tools: package_search_hybrid() package_search_grep() package_search_read_file() Add it to Cursor, Claude Code, VS Code, and Codex in 5 seconds
00:00 - A deep dive on wal3 - Chroma's open-source write-ahead log built on object storage. Featuring: - a 30-year-old lock-free algorithm - Amazon S3's newest conditional writes feature - a novel checksumming technique called setsum
- Announcing the first ever ChatGPT Plugins Hackathon! San Francisco, 4/8 - 4/9. Two days, 100 hackers, the future of AI.
- Announcing the Chroma CLI! - Browse data in the terminal - Copy data between chroma servers - Install sample apps - Create databases - Login to Chroma Cloud - **more coming soon** pip install -U chromadb npm install -g chromadb
00:00 - We all have access to the same models, what coding agent you use matters. For example, @FactoryAI with Claude Sonnet 4 can out perform Claude Code with Claude Opus 4. Learn about how Chroma Cloud plays a role in Factory's context engineering strategy: trychroma.com/company/factor…
- Prompting isn’t engineering, argues @isaacbmiller1. “Context engineering is how we actually build reliable AI systems.” Learn how @DSPyOSS turns prompts into programs.
00:00 - NEW: @0interestrates on building @juliusai also on YouTube and Apple Podcasts full transcript and timestamps: studios.trychroma.com/rahul-on-julius
00:00
