shipping.buzz
Sign in

Radar for context engineers

109 curated tools and processes, grouped by the six jobs of context engineering. Every number links to its source.

Retrieve

Pull the right outside knowledge into context, just in time: search, RAG, embeddings, rerankers, docs and code fetchers.

30 tools
  • BGE-M3
  • Chonkie
  • Chroma
  • Context7
  • +26

Memory

Keep what matters outside the window across turns and sessions, and bring it back when needed.

13 tools
  • Basic Memory
  • Beads
  • claude-mem
  • Cognee
  • +9

Tools & MCP

Give agents actions and live data through tools: MCP servers, SDKs, registries and tool design.

17 tools
  • Agent Skills (anthropics/skills)
  • Chrome DevTools MCP
  • Code execution with MCP
  • Composio
  • +13

Compression

Fit more signal into fewer tokens: compaction, summarization, token-efficient formats, repo packers, caching.

13 tools
  • Attention budget
  • code2prompt
  • Compaction
  • Context editing
  • +9

Sub-agents & orchestration

Split work across agents with clean, isolated contexts: agent frameworks, sub-agents, handoffs, workflows.

17 tools
  • Agent Development Kit (ADK)
  • Agno
  • AI SDK (Vercel)
  • BAML
  • +13

Evals & observability

See what went into the context and whether it worked: tracing, evals, regression tests, token and cost tracking.

19 tools
  • Arize Phoenix
  • Braintrust
  • Context clash
  • Context confusion
  • +15

Retrieve

30See all 30 →

Pull the right outside knowledge into context, just in time: search, RAG, embeddings, rerankers, docs and code fetchers.

Screenshot of the BGE-M3 website

BGE-M3

Multilingual embedding model that does dense, sparse and multi-vector retrieval in one model (BAAI).

tool

Website captured Oct 19

Screenshot of the Chroma website

Chroma

Open-source search infrastructure for AI: embed, store and query documents for retrieval.

tool

Website captured Oct 19

Disclosure: the operator of shipping.buzz is a Qdrant Star Ambassador. No manual overrides apply to vector databases.

Contextual retrieval

Prepend chunk-specific context before embedding and BM25 indexing. Anthropic measured 49% fewer failed retrievals, and 67% fewer with reranking.

process

    Memory

    13See all 13 →

    Keep what matters outside the window across turns and sessions, and bring it back when needed.

    Screenshot of the Basic Memory website

    Basic Memory

    Local Markdown knowledge base that AI assistants read and write through MCP, so you stop re-explaining projects.

    tool

    Website captured Oct 19

    File system as context

    Treat files as unlimited, persistent memory: write big observations to disk and keep only paths in context; recite a todo.md to keep goals in focus.

    process

      Tools & MCP

      17See all 17 →

      Give agents actions and live data through tools: MCP servers, SDKs, registries and tool design.

      Code execution with MCP

      Expose MCP tools as code the agent calls from a sandbox, so only the definitions and results it needs enter context.

      process

        Compression

        13See all 13 →

        Fit more signal into fewer tokens: compaction, summarization, token-efficient formats, repo packers, caching.

        Attention budget

        The finite attention an LLM spends across its context; every new token draws it down, so context must be curated.

        term

          Compaction

          When a conversation nears the window limit, summarize it and restart a fresh window with the summary.

          process

            Context editing

            Automatically clearing stale tool calls and results from the context as it nears its limit (a Claude Developer Platform feature).

            term

              KV-cache hit rate

              The share of prompt tokens served from the model's key-value cache; higher means lower latency and cost.

              term

                KV-cache-friendly context

                Keep the prompt prefix stable and the context append-only so cached tokens get reused.

                process

                  Sub-agents & orchestration

                  17See all 17 →

                  Split work across agents with clean, isolated contexts: agent frameworks, sub-agents, handoffs, workflows.

                  Context engineering

                  The set of strategies for curating and maintaining the optimal set of tokens during LLM inference, including everything that lands in context outside the prompt.

                  term

                    Evals & observability

                    19See all 19 →

                    See what went into the context and whether it worked: tracing, evals, regression tests, token and cost tracking.

                    Context clash

                    When new information or tools in the context conflict with other information already there.

                    term

                      Context confusion

                      When superfluous content in the context is used by the model to produce a low-quality response.

                      term

                        Context distraction

                        When context grows so long that the model over-focuses on it and neglects what it learned in training.

                        term

                          Context poisoning

                          When a hallucination or other error makes it into the context and keeps getting referenced.

                          term

                            Context rot

                            The drop in a model's ability to recall and use information as the number of tokens in its context grows.

                            term