All tools
Hybrid code review that puts deterministic rules first and the LLM second — the only ordering that survives an enterprise security review.
Git worktree plumbing for running several coding agents at once without them wrecking each other's working tree.
A curated set of reusable skills for coding agents — the difference between an agent that finishes tasks and one that finishes them your way.
The terminal-native agent that made agentic coding mainstream — and the reference point every other coding agent is measured against.
Runs many coding agents in parallel while still using the subscriptions you already pay for — the cost model is the product.
A routing layer that keeps your coding agent alive when one provider rate-limits you — worth it for the fallback alone.
Strips the tell-tale rhythm of model output from generated text — useful, and a reminder that the tells are now well known.
An explicit, readable list of the twenty-odd patterns that make text read as generated — better as a checklist than as a filter.
The shortest distance from pip install to a working retriever — which is why nearly every RAG tutorial starts here.
Validates model output against a schema instead of hoping — and re-asks when validation fails.
Gives an agent continuity across sessions — the missing piece once users expect it to remember them.
LLM traces as standard OpenTelemetry spans — so they land in the observability stack you already pay for.
The last few percent of GPU throughput, paid for in build complexity and hardware lock-in.
Document-to-RAG pipeline in a box, from a team that runs it at Tencent scale.
The unglamorous parsing layer that decides whether your RAG works at all.
The front end you hand to users when the model layer is already done.
Multi-user, multi-provider chat platform with agents and MCP already wired in.
The format question for agent capabilities is being settled here, and it is just a folder.
Web access for agents without paying per-call — including the platforms with no usable API.
Treats the context window as a budget with a line item, not a bucket you keep pouring into.
Puts the specification back in front of the code, which is the only way agent output stays reviewable.
Not a tool but a method: encode how your team works, then let the agent follow it.
Vendor-published plugins for the jobs knowledge workers actually do — a usable starting template.
High-throughput LLM inference engine with PagedAttention — the default choice when you need to squeeze a GPU.
One command to run an LLM on a laptop — the fastest way to get a model in front of a customer.
CPU-first inference in plain C/C++ — runs where a GPU cannot go.
HuggingFace's Rust-based serving stack with tensor parallelism and streaming built in.
Serving engine built for structured outputs and heavy prefix reuse.
One OpenAI-shaped interface for 100+ model providers, plus a proxy that tracks spend per key.
Data framework for ingestion, indexing and retrieval — strongest on document-heavy RAG.
Turns PDFs, HTML and scans into clean structured elements your retriever can actually use.
End-to-end RAG engine with template-based chunking you can show to a customer.
Model agents as explicit state graphs — the difference between a demo loop and a controllable system.
Self-hostable LLMOps platform with visual workflows, RAG and prompt management in one box.
Role-based multi-agent orchestration — readable when you have to explain it to a manager.
Conversation-driven multi-agent framework with strong code-execution tooling.
The largest integration surface in LLM tooling — most useful when you need a connector today.
Self-hostable tracing, evals and prompt management — the observability layer most teams forget to build.
Metric suite for RAG: faithfulness, context precision, recall — the numbers you need before a go-live review.
Notebook-first observability with clustering that surfaces failure modes you did not think to test.
Drop-in proxy that logs every request and shows cost per user, per feature, per day.
Rust vector database with payload filtering — strong when metadata matters as much as similarity.
Distributed vector database built for billion-scale — the choice once one node stops being enough.
Vector database with built-in embedding modules — less glue code in your ingestion path.
Vectors inside the Postgres you already run — the right answer until it is not.
Nothing here yet. The next crawl fills this up.