contextweaver

<!-- mcp-name: io.github.dgenio/contextweaver -->

The MCP context gateway for tool-heavy agents. Drop contextweaver in front of your MCP servers and the model sees a bounded ChoiceCard shortlist instead of every tool schema, plus an artifact-backed firewall that swaps a huge raw tool result for a compact summary. Deterministic, no model in the loop, and 42-84 % fewer prompt tokens on the committed benchmarks.

Who it's for: anyone whose agent — Claude Desktop, Cursor, VS Code, or a custom loop — keeps tripping over "too many tools" or "a 16 KB tool result blew up my prompt."

uvx contextweaver demo --scenario killer  # zero-install trial

# Or install it:
pip install contextweaver
python -c "import contextweaver; print(contextweaver.__version__)"
contextweaver demo --scenario killer   # 60-second taste — no API key, no network

Use it for real → the [MCP gateway quickstart](docs/recipes/index.md) (Claude Desktop / Copilot / custom MCP clients), backed by the MCP Context Gateway architecture. Already have a loop and not sure which piece you need? The two engines also work routing-only or firewall-only. For day-to-day operating guidance, see the Daily Driver guide; for deployment boundaries, see the MCP Gateway Security Model.

<p align="center"> <img src="docs/assets/hero.svg" alt="contextweaver architecture: Context Engine plus Routing Engine, with the Context Firewall storing large tool outputs out of band and the Routing Engine narrowing a 100-tool catalog to 5 ChoiceCards."/> </p>

1150+ tests passing · minimal core dependencies · deterministic by default · Python 3.10–3.13

#### More tools ≠ better answers

<p align="center"> <img src="docs/assets/context_rot.svg" width="660" alt="Context-rot curve: as the tool catalog grows from 83 to 1328 tools, a naive route prompt carries every schema (line climbs on a log scale) while contextweaver stays flat at 5 ChoiceCards; contextweaver's correct-tool recall@5 erodes from 36 percent to 10 percent as distractor tools accumulate."/> </p>

As an agent's tool catalog grows, a naive "show every schema" route prompt balloons while the right tool gets harder to find — context rot. contextweaver keeps the model-visible surface bounded (5 ChoiceCards, not 1,328 schemas), so the route prompt stays flat and deterministic. Reproduce the curve with no API key: docs/context_rot.md.

<p align="center"> <img src="docs/assets/demo.svg" alt="Animated terminal recording of python -m contextweaver demo: load a 40-tool catalog, build a 9-node routing graph, narrow to 5 ChoiceCards for the query 'find unpaid invoices and send a reminder email', build a phase-answer context pack, and print the 321-character compiled prompt."/> </p>

<p align="center"> <img src="docs/assets/before_after.svg" alt="Before vs after token comparison from examples/before_after.py: 417 raw prompt tokens without contextweaver vs 126 final prompt tokens with contextweaver — a 70 percent reduction, 291 tokens saved, budget compliant."/> </p>

📖 Docs · 🎬 Showcase · 🧩 Where it fits · 🗺️ Ecosystem map · ❓ FAQ · 📊 Scorecard · 📈 Adopter benchmark report · 🧭 Which pattern fits? · 🛠 Cookbook · 🍳 Recipes · 📉 Context rot demo · 🎬 Replay demo (.cast)

Part of the Weaver Stack

contextweaver is the context layer of the Weaver Stack — small, deterministic, independently-usable building blocks for tool-using agents. The core request path runs:

contextweaver ─▶ ChainWeaver ─▶ agent-kernel ─▶ agentfence

The contextweaver → ChainWeaver handoff is advisory: contextweaver routes (it recommends a capability) and ingests results behind its firewall; the runtime owns authorization and execution. A runnable end-to-end example — route a catalog of tools + imported ChainWeaver flows, hand the selection to a (stubbed) ChainWeaver runtime, then ingest the result — lives at examples/architectures/contextweaver_to_chainweaver/, and the contract boundary is documented in docs/weaver_spec_mapping.md.

Adjacent tools: vibeguard (code-diff safety gate), lessonweaver (lesson capture), and skdr-eval (offline evaluation). Every piece works standalone — contextweaver has no hard dependency on any sibling, so you can use it on its own or slot it into the stack. See the Ecosystem Map for how the pieces compose.

The 60-second failure mode

See why a naive tool-using agent loop breaks down — and what contextweaver does about it — in one command (no API keys, no network):

contextweaver demo --scenario killer

An internal ops agent with 100 tools and a running conversation is asked to "find unpaid invoices, check the account notes, and draft a reminder." A naive loop pays for all 100 tool descriptions, the full history, and a huge raw tool result at once:

Full walkthrough: The 60-second failure mode. For the same story as a runnable, inspectable script, see the catalog showcase architecture.

The Problem

Even with 200K-token context windows, dumping everything into the prompt is expensive, slow, and degrades output quality. More context ≠ better answers — context engineering (deciding what the model sees, when, and at what cost) is the lever that actually moves quality and latency.

Imagine a tool-using agent with a 100-tool catalog and a 50-turn conversation history. At each step the agent must answer four questions:

1. Route — which tool should I call?
2. Call — what arguments?
3. Interpret — what did it return?
4. Answer — how do I respond to the user?

Naive approach A — concatenate everything:

100 tool schemas (≈50k tokens) + 50 turns (≈30k tokens) = 80k tokens
Cost: $0.48/request at GPT-4o rates  ·  Latency: 3–5s TTFT
Quality: LLM loses focus — needle-in-haystack accuracy drops with context size
Token limit: 8k → 10× overflow

Naive approach B — cherry-pick manually:

Pick 10 tools, last 5 turns → lose dependency chains
Agent hallucinates tool calls, repeats questions, forgets context

contextweaver approach — phase-specific budgeted compilation:

Route phase:  5 tool cards (≈500 tokens), no full schemas
Answer phase: 3 relevant turns + dependency closure (≈2k tokens)
Result:       2.5k tokens, complete context, deterministic
Cost:         41.6 %-84.3 % fewer prompt tokens [^naive-baseline]  ·  Latency: sub-second  ·  Quality: relevant context only

[^naive-baseline]: Measured against the "concatenate all tool schemas + full conversation history" baseline using tiktoken.cl100k_base on the six committed benchmark scenarios. Range 41.6 %-84.3 %, average 64.3 %. Reproducible via make benchmark-matrix && make scorecard — see the vs. naïve concat baseline section of benchmarks/scorecard.md and the methodology in scripts/baseline_naive.py.

See examples/before_after.py for a runnable side-by-side comparison.

How contextweaver Solves It

contextweaver provides two cooperating engines:

                ┌────────────────────────────┐
  Events ──────>│      Context Engine         │──> ContextPack (prompt)
                │  candidates → closure →     │
                │  sensitivity → firewall →   │
                │  score → dedup → select →   │
                │  render                     │
                └────────────────────────────┘
                           ▲ facts / episodes
                ┌──────────┴─────────────────┐
  Tools ───────>│      Routing Engine         │──> ChoiceCards
                │  Catalog → TreeBuilder →    │
                │  ChoiceGraph → Router       │
                └────────────────────────────┘

Context Engine — eight-stage pipeline:

1. generate_candidates — pull phase-relevant events from the log for this request.
2. dependency_closure — if a selected item has a parent_id, include the parent automatically.
3. sensitivity_filter — drop or redact items at or above the configured sensitivity floor.
4. apply_firewall — tool results are stored out-of-band; large outputs are summarized/truncated before prompt assembly.
5. score_candidates — rank by recency, tag match, kind priority, and token cost.
6. deduplicate_candidates — remove near-duplicates using Jaccard similarity.
7. select_and_pack — greedily pack highest-scoring items into the phase token budget.
8. render_context — assemble final prompt string with BuildStats metadata.

Routing Engine — four-stage pipeline:

1. Catalog — register and manage SelectableItem objects.
2. TreeBuilder — convert a flat catalog into a bounded ChoiceGraph DAG.
3. Router — beam-search over the graph; deterministic tie-breaking by ID.
4. ChoiceCards — compact, LLM-friendly cards (never includes full schemas).

Also works as routing-only or firewall-only

The MCP gateway is the headline, but those are really two cooperating engines you can adopt independently — a context compiler and a tool router. Reach for whichever your agent needs:

Not sure which piece fits? The which-pattern decision tree maps each symptom (long conversations → full pipeline; 50+ tools → routing-only; huge tool outputs → firewall-only) to one concrete next step.

When not to use contextweaver

contextweaver is a context compiler for tool-using agents — its value scales with the size of the catalog and the length of the conversation. Reach for something simpler when none of that pressure exists:

• Small tool catalogs (≤ 5 tools). Dumping every schema into the prompt

costs a few hundred tokens. Building a routing graph and running beam search adds latency and a dependency you don't need.

• Single-shot Q&A or one-turn agents. With no history to compact and no

follow-up phases (call / interpret / answer), phase-aware budgeting is dead weight — pass the user's message straight to the model.

• Tiny tool outputs. If every tool_result is comfortably under the

configured firewall_threshold (default 2000 characters), the context firewall correctly no-ops — you're paying the conceptual cost of the firewall for zero token savings.

• Full context is cheaper than the engineering. If your naïve prompt

fits comfortably under the model's context window and your token bill is not a concern, the before/after scorecard numbers won't move the needle.

• You need non-deterministic, LLM-driven routing. contextweaver's

routing engine is deterministic by design (tie-break by sorted ID). If you want an LLM to decide which tool to call from free-form reasoning, LangGraph or a plain tool_choice="auto" call is a better fit — see docs/comparison.md for the trade-offs.

If you're not sure, the 10-minute Quickstart below is the cheapest way to find out: a 40-tool catalog and a 50-turn transcript is the smallest scenario where contextweaver clearly pays for itself.

Quickstart

Install

Try the CLI without installing it:

uvx contextweaver demo --scenario killer

Or install it persistently:

pip install contextweaver

contextweaver ships with a minimal, opinionated core: tiktoken, PyYAML, rank-bm25, mcp, jsonschema, Typer, and Rich. These power token budgeting, YAML catalog/config files, the default lexical retrieval backend, the MCP proxy/gateway runtime, schema validation, and the CLI.

Optional capabilities are gated behind extras so the core install stays small:

Some extras are install-contract markers rather than dependency bundles: tokenizers, sqlite, and e2e-eval are intentionally empty today because the current implementations use core dependencies or the Python standard library. They stay user-facing so requirements files can opt into the capability surface without changing when future implementation-specific packages are added.

Or from source:

git clone https://github.com/dgenio/contextweaver.git
cd contextweaver
pip install -e ".[dev]"

Adopting in 5 lines from an existing OpenAI / Anthropic / Gemini agent

<!-- snippet: skip (illustrative; messages is the caller's existing history) -->

from contextweaver.adapters.openai_messages import from_openai_messages
from contextweaver.context.manager import ContextManager
from contextweaver.types import Phase

mgr = ContextManager()
from_openai_messages(messages, into=mgr)   # also: from_anthropic_messages / from_gemini_contents
pack = mgr.build_sync(phase=Phase.answer, query="...")

See Adopting from an existing chat history for the full snippet (including the to_* inverse adapters for round-tripping back into the provider SDK).

10-Minute Quickstart

For a guided setup with prerequisites, three runnable examples, expected output, and next steps, see docs/quickstart.md.

Already have an agent and not sure which piece you need? See Which pattern fits my use case? — a symptom-based decision tree (long conversations → full pipeline; 50+ tools → routing-only; huge tool outputs → firewall-only) that points each branch to one concrete next step.

Minimal agent loop

from contextweaver.context.manager import ContextManager
from contextweaver.types import ContextItem, ItemKind, Phase

mgr = ContextManager()
mgr.ingest(ContextItem(id="u1", kind=ItemKind.user_turn, text="How many users?"))
mgr.ingest(ContextItem(id="tc1", kind=ItemKind.tool_call,
                       text="db_query('SELECT COUNT(*) FROM users')", parent_id="u1"))
mgr.ingest(ContextItem(id="tr1", kind=ItemKind.tool_result,
                       text="count: 1042", parent_id="tc1"))

pack = mgr.build_sync(phase=Phase.answer, query="user count")
print(pack.prompt)   # budget-aware compiled context
print(pack.stats)    # what was kept, dropped, deduplicated

Route a large tool catalog

<!-- snippet: skip (illustrative; needs a real catalog.json on disk) -->

from contextweaver.routing.catalog import Catalog, load_catalog_json
from contextweaver.routing.tree import TreeBuilder
from contextweaver.routing.router import Router

catalog = Catalog()
for item in load_catalog_json("catalog.json"):
    catalog.register(item)

graph = TreeBuilder(max_children=10).build(catalog.all())
router = Router(graph, items=catalog.all(), beam_width=3, top_k=5)
result = router.route("send a reminder email about unpaid invoices")
print(result.candidate_ids)

Runtime Loop (4 Phases)

For a complete route -> call -> interpret -> answer reference flow, see:

• examples/full_agent_loop.py for a runnable end-to-end script.
• docs/guide_agent_loop.md for the flow diagram, pseudo-code, and module map.

The runtime loop example demonstrates:

1. Route-phase prompt assembly with ChoiceCards.
2. Call-phase prompt assembly with selected tool schema hydration.
3. Interpret-phase firewall behavior (large tool output summarized into context).
4. Answer-phase context composition with accumulated history and result envelopes.

Framework Integrations

Looking for "where does contextweaver fit alongside my runtime?" — start with the How contextweaver Fits positioning page, then jump into the Cookbook for copy-paste recipes.

The Code adapter column lists the importable adapter module and its optional extra; its plain-dict conversion path works without the extra installed. _Guide only_ rows ship a written integration guide but no dedicated tools → catalog adapter yet (issue #401).

Core Concepts

See docs/concepts.md for the full glossary, docs/architecture.md for pipeline detail and design rationale, and docs/troubleshooting.md for common issues, debugging techniques, and performance optimisation tips.

Why Trust contextweaver?

1. Test Coverage & Reliability

contextweaver is built for production use with comprehensive quality gates:

• Broad regression suite across all modules — context pipeline, routing engine, firewall,

adapters, stores, CLI, sensitivity enforcement

• mypy strict type checking — zero errors across all source files
• ruff clean linting — zero warnings
• CI pipeline on every pull request and on pushes to main (see workflows)
• Deterministic by default — tie-break by ID, sorted keys; identical inputs always

produce identical outputs. Configurable retrieval backends (TF-IDF, BM25, fuzzy) preserve determinism within each mode.

• Public benchmark scorecard — top-k recall, token savings, and routing latency at

catalog sizes 50 / 83 / 1000, plus context pipeline metrics across six reference scenarios. See benchmarks/scorecard.md (regenerate with make scorecard) and the adopter-facing benchmark report.

Run the full suite yourself:

git clone https://github.com/dgenio/contextweaver.git
cd contextweaver
pip install -e ".[dev]"
make ci  # fmt + lint + type + test + schemas-check + example + demo (all pass)

Most agent libraries fail unpredictably when context exceeds token limits. contextweaver's deterministic design and comprehensive test coverage ensure your agent behaves the same way every time — critical for debugging, testing, and production deployment.

2. Design Rationale

Every architectural choice was made for a reason:

These aren't accidental features. They are design decisions optimized for reliability, extensibility, and production use. A minimal, audited core-dependency set means you can adopt contextweaver without disrupting your existing stack.

See docs/architecture.md for full pipeline detail and design rationale.

3. Standardization via Protocol Support

contextweaver supports both emerging agentic protocols out of the box:

MCP (Model Context Protocol) — convert tool definitions and results into native contextweaver types:

• Compatible with any MCP server (Claude Desktop, VS Code, custom servers)
• Structured content, output schemas, binary artifacts, and per-part annotations all handled
• ingest_mcp_result() for one-call result ingestion with automatic artifact persistence

A2A (Agent-to-Agent) — multi-agent session management with unified context:

• Agent cards converted to SelectableItem for routing
• Cross-agent session loading via load_a2a_session_jsonl()
• A2A results stored in ResultEnvelope with facts and artifact handles

weaver-spec — canonical contracts for the Weaver Stack (contextweaver, ChainWeaver, agent-kernel):

• Lossless to_weaver_* / from_weaver_* round-trips for SelectableItem,

ChoiceCard, RoutingDecision, and Frame (via ResultEnvelope)

• weaver_contracts is an opt-in dep — pip install 'contextweaver[weaver-spec]'
• Validated in CI on every PR against the JSON Schemas at

raw.githubusercontent.com/dgenio/weaver-spec/main/contracts/json/ (the source the gate fetches; the same documents are also published at https://weaver-spec.dev/contracts/v0/)

contextweaver is designed as a protocol-friendly context management layer for tool-using agents. Supporting MCP, A2A, and weaver-spec keeps the integration boundary explicit as these protocols mature.

• MCP Integration
• A2A Integration
• weaver-spec mapping
• MCP Specification
• weaver-spec

4. Framework Agnostic

contextweaver works with any LLM provider and any agent framework:

• LLM providers: OpenAI, Anthropic, Google, open-source models — no API keys required

by contextweaver itself

• Agent frameworks: LlamaIndex, LangChain, LangGraph, OpenAI Agents SDK, Google ADK,

Pipecat, custom loops

• No vendor lock-in: stdlib-only core; no cloud dependencies; runs anywhere Python 3.10+ runs

See the Framework Integrations table and the interop guide for supported adapters and positioning.

You are not locked into a specific framework or LLM provider. contextweaver is a layer beneath frameworks — context management as a composable primitive.

5. Stability & Compatibility

contextweaver is currently Alpha in package metadata because the project is still clarifying its pre-1.0 stability boundary. The core context/routing APIs are intentionally deterministic and heavily tested; newer runtime surfaces such as gateway commands, adapters, and extras are called out as experimental where appropriate. See the detailed stability and 1.0 readiness checklist.

Adopting a library is a long-term commitment. The stability page makes the Alpha/Beta/1.0 line explicit so teams can decide which surfaces are ready for their risk tolerance.

#### Weaver Spec Compatibility

contextweaver implements weaver_contracts >= 0.2.0, < 1.0 (canonical contracts for the Weaver Stack — see weaver-spec).

Contract adapters (pip install 'contextweaver[weaver-spec]'):

from contextweaver.adapters.weaver_contracts import (
    to_weaver_routing_decision,
    from_weaver_routing_decision,
    to_weaver_frame,
    from_weaver_frame,
)

Round-trips are lossless via a reserved metadata["_contextweaver"] payload; see docs/weaver_spec_mapping.md for the full mapping table.

CI conformance — every PR runs scripts/weaver_spec_conformance.py, which does both a Python round-trip (cw → spec → cw == cw) and JSON-Schema validation. CI fetches the schemas from raw.githubusercontent.com/dgenio/weaver-spec/main/contracts/json/, which mirrors the published documents at https://weaver-spec.dev/contracts/v0/ (same content, different host). Run locally with make weaver-conformance.

6. Roadmap & Community

Current package version: 0.16.0.

Recent milestones:

Community:

• GitHub Discussions — ask questions, share patterns
• GitHub Issues — report bugs, request features
• CHANGELOG — track every release

contextweaver is under active development with a clear roadmap. The core is usable today; the project remains Alpha until the Beta readiness checklist is complete or intentionally revised.

7. Comparison

_Snapshot of the launch landscape as of 2026-05-31 — see footnotes for the versions referenced and the evidence behind each non-trivial claim. Will be refreshed each minor release._

[^cw-route]: contextweaver.routing.router.Router ships a four-stage pipeline (retrieve → rerank → navigate → pack) with deterministic tie-break by id. Locked by tests/test_cards.py::test_make_choice_cards_byte_identical_stable_order. [^cw-bench]: Range from the committed scorecard (benchmarks/scorecard.md) using tiktoken.cl100k_base against the naïve baseline (scripts/baseline_naive.py). Average 64.3 %; min 41.6 % on long_conversation.jsonl; max 84.3 % on tiny_payload.jsonl. [^cw-fire]: contextweaver.context.firewall.apply_firewall plus ArtifactRef drilldown selectors (head / lines / json_keys / rows). See docs/context_firewall.md and the firewall_drilldown_recipe. [^cw-det]: Determinism is an invariant — see docs/agent-context/invariants.md and make scorecard-check in the CI gate. [^cw-mcp]: src/contextweaver/adapters/mcp_proxy.py, mcp_gateway.py, mcp_proxy_server.py, mcp_gateway_server.py. Bound by docs/gateway_spec.md. [^lg-mem]: LangGraph 0.6 docs ("Memory"): ConversationSummaryMemory requires an LLM round-trip to produce a summary; output is non-deterministic across runs even with temperature=0 due to model jitter. [^li-mem]: LlamaIndex 0.11 docs ("Chat memory"): ChatMemoryBuffer(token_limit=...) truncates oldest-first; no phase awareness and no dependency closure.

Most agent frameworks offer one or two of these capabilities. contextweaver ships all five as a composable, framework-agnostic layer that runs under whichever framework you already have.

CLI

contextweaver ships with a CLI for quick experimentation:

contextweaver demo                                    # end-to-end demonstration
contextweaver demo --scenario killer                  # the 60-second failure mode (100 tools + huge output)
contextweaver init                                    # scaffold config + sample catalog
contextweaver build --catalog c.json --out g.json    # build routing graph
contextweaver route --graph g.json --catalog c.json --query "send email"
contextweaver print-tree --graph g.json
contextweaver ingest --events session.jsonl --out session.json
contextweaver replay --session session.json --phase answer
contextweaver inspect --session session.json --format markdown
contextweaver mcp inspect --catalog c.json --format json
contextweaver mcp serve --catalog c.json --diagnostics gateway.jsonl --quiet
contextweaver mcp stats --events gateway.jsonl

Examples

make example   # run all examples

FAQ

Q: What token budgets should I use? Start with the defaults (route=2000, call=3000, interpret=4000, answer=6000). Inspect pack.stats after each build and increase any phase that drops too many items.

Q: My tool result was summarized. Why? The context firewall intercepts every tool_result item (not just large ones). Raw data is stored out-of-band; access it via mgr.artifact_store.get("artifact:<item_id>"). Provide a custom Summarizer to control how the summary is generated.

Q: How do I debug what was kept or dropped? Inspect pack.stats (a BuildStats object) after every build_sync() / build() call: included_count, dropped_count, dropped_reasons, dropped_items, dedup_removed. Completed builds satisfy included_count + dropped_count == total_candidates.

Q: Does this work with [framework X]? Yes, contextweaver is framework-agnostic — it compiles context; you send pack.prompt to any LLM or framework. See dedicated guides for MCP, A2A, LlamaIndex, LangChain + LangGraph, OpenAI Agents SDK, Google ADK / Vertex AI, Pipecat, CrewAI, Pydantic AI, smolagents, Agno, Microsoft Agent Framework, OpenAPI, and Agent Skills. If your runtime isn't listed, the bring-your-own-tools cookbook recipe is the canonical starting point.

Q: What's the performance overhead? Typically 10–50 ms for a context build (depends on event log size and deduplication). For real-time / async agents, run build_sync() in a worker thread (e.g. await asyncio.to_thread(mgr.build_sync, phase, query)) so the synchronous pipeline does not block the event loop. If an offline or air-gapped run prints a tiktoken cl100k_base encoding unavailable warning, see the troubleshooting note; the fallback keeps budget enforcement deterministic.

See docs/troubleshooting.md for the full troubleshooting guide, debugging techniques, optimisation tips, and 10+ common issues with solutions.

Development

make fmt      # format (ruff)
make lint     # lint (ruff)
make type     # type-check (mypy)
make test     # run tests (pytest)
make example  # run all examples
make demo     # run the built-in demo
make ci       # all validation targets, including schemas-check

See CONTRIBUTING.md for setup instructions, and docs/contributing_paths.md to pick a contribution path (docs, adapters, benchmarks, examples, good-first-issues) by how much time you have. All contributors agree to the Code of Conduct.

Roadmap

See CHANGELOG.md for the detailed release history.

License

Apache-2.0