Item detail

pivanov/ctx-wire

pivanov/ctx-wire is a token-saving middleware for ai c that RepoRadar is tracking in its MIT `ctx-wire` middleware that sits between an A section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.2 out of 10.

Score8.1
Popularity63.0
Risklow
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum7.0
Maturity7.7
Open-source/build8.4
Evidence7.2
Workflow potential9.2
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers running AI coding agents (Claude Code, Codex, Devin, Cursor, OpenCode) who are burning tokens on noisy command output: ctx-wire is the MIT-licensed middleware that compresses noisy command output with declarative filters, scrubs secrets before the model sees them, spools full scrubbed logs on failure, and reports exactly how many bytes + tokens were saved broken down by progr

Who should use it

Developers running AI coding agents (Claude Code, Codex, Devin, Cursor, OpenCode) who are burning tokens on noisy command outputUsers who want transparent install without changing the agent's command interface (`ctx-wire init <agent>` wires it through the agent's hook or PATH shims)Security-conscious teams who need secret-scrubbing before the model sees command output (auth tokens, JWTs, AWS keys, etc. are redacted automatically)Users with snapshot-heavy MCP servers (chrome-devtools, Playwright) who need verbose browser snapshots compressed with the raw result spooled locallyEngineering teams who want a measurable token-savings report (`ctx-wire gain` reports bytes and tokens saved by program and by agent, so ROI is observable)Users with steering-only agents that don't expose a hook (PATH shims handle the steering-only case too)Teams running CI/CD pipelines through AI coding agents where the model needs to act on test failures (full scrubbed logs are spooled on disk for failure debugging)Adopters who want declarative filters that are inspectable and tunable (the filter set is data, not opaque behavior — a team can review and extend it without forking the binary)

Who should skip it

Skip pivanov/ctx-wire if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

pivanov/ctx-wire is tracked by RepoRadar as a token-saving middleware for ai c in the MIT `ctx-wire` middleware that sits between an A section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, pivanov/ctx-wire is strongest on workflow potential (9.2) and practical usefulness (9.0) and weakest on momentum (7.0) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned pivanov/ctx-wire a composite score of 8.1 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 63.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Risk explanation

**Secret-scrubbing is best-effort, not a substitute for a real secret manager.** ctx-wire's secret-scrubber redacts common patterns (auth tokens, JWTs, AWS keys) before the model sees the output, but the maintainer does not claim it's a substitute for a real secret manager (Vault, AWS Secrets Manager, Doppler). Adopters in regulated environments should keep secrets out of command output entirely (use a secret manager + env-var injection) and treat ctx-wire's scrubber as a defense-in-depth layer, not the primary secret-handling layer; **63 stars, 0 forks, 0 subscribers, no release yet.** ctx-wire is at 63 stars with no release tag and last push 2026-06-24 — moving fast but early-stage. Adopters in production should pin a specific commit (not a release tag) and monitor the changelog for breaking changes to the declarative filter set or the on-disk spool format; users who need a more battle-tested output-compression middleware should evaluate existing solutions (e.g. custom shell wrappers, agent-specific filter plugins) first and consider ctx-wire for new deployments where the declarative-filter + secret-scrubbing + MCP-wrap combination is the value proposition; **Transparent install via PATH shims affects every command in the steering-agent case.** When the agent doesn't expose a hook, ctx-wire installs PATH shims that wrap every shell command the agent runs — this changes the system PATH and could affect non-agent commands run in the same shell. Users who adopt PATH-shim mode should either (1) isolate the agent to its own shell session / container, or (2) audit the shim set after install to confirm only the intended programs are wrapped.

Evidence links

Closest alternatives / related signals

ctx-wirectxwirepivanovtoken-savingstoken-optimizationcontext-windowcommand-outputoutput-compression