Entroly

中文 • 日本語 • 한국어 • Português • Español • Deutsch • Français • Русский • हिन्दी • Türkçe

Entroly

Know exactly what your AI agent saw.
Entroly creates replayable Context Commits: content-addressed proof of the evidence selected, omitted, and kept recoverable for each model request.

_{Drop-in for Cursor, Claude Code, Codex, Aider + 34 more and custom providers — 60s, no code changes.}

_{Auditable context control plane · every answer gets a receipt: what was used, what was omitted, why, and the risks that remain · local-first · Rust + WASM · reversible · savings measured on real workloads}

pip install -U entroly && cd /your/repo && entroly verify-claims && entroly simulate

Get started · Proof · Integrations · What's inside · Architecture · For teams · Limitations

Deciding whether to star? Run the no-key proof first: entroly verify-claims && entroly simulate.
_{If it finds meaningful savings or gives you auditable receipts on your repo, star it so other agent builders can find it. If it does not, open an issue with the verification JSON.}

What it does

Entroly is an auditable context control plane for AI agents. It decides what context to send, records what it left out, and produces a receipt you can inspect before trusting a hard multi-file answer.

Most compression tools shrink whatever text the agent already chose. Entroly starts one step earlier: it chooses the highest-value evidence first, compresses only after selection, keeps originals recoverable, then verifies the answer against the evidence.

• Receipts - every selection run can explain selected chunks, omitted nearby evidence, dependency links, fingerprints, token ratio, and residual risks.
• Select - ranks your repo or document set, then sends the answer-relevant context under a token budget.
• Verify - WITNESS checks the model's answer against the evidence it was given and flags unsupported claims. $0, ~3 ms, no extra API call.
• Route - sends easy, repeated tasks to a cheaper model and keeps the flagship for hard ones (opt-in, fail-closed).
• Cache-align - keeps the injected prefix byte-stable so provider prefix caches can keep hitting where terms and API shape allow it.
• Learn - improves which files it picks for your workflow from local feedback. No embeddings API, no training job.

Use it however you work: wrap your agent, run it as a proxy, plug it in as an MCP server, or import the library.

Why teams care

Product surface

Entroly ships as a full local runtime, not one proxy command:

Under the hood, the Python control plane is backed by a Rust/WASM engine with BM25, entropy scoring, SimHash dedup, dependency graphs, knapsack/IOS selection, EGSC caching, PRISM learning, SAST, QCCR, EICV, witness checks, CogOps, cache economics, and memory primitives.

See the full code-derived map in docs/product-surface.md.

How it works (30 seconds)

your agent  ──►  Entroly (local)  ──►  LLM provider
                 │
                 ├─ rank the repo        (BM25 + entropy + dep-graph)
                 ├─ select under budget  (knapsack, reversible)
                 ├─ emit receipt         (included, omitted, risks)
                 ├─ cache-align prefix    (keep provider cache hot)
                 └─ verify the reply      (WITNESS hallucination guard)

Critical files go in full. Supporting files become signatures. Everything else becomes a reference you can expand on demand — so the model gets a broader view of your codebase in a smaller prompt. Nothing is lost: every compressed fragment is fully retrievable.

Get started (60 seconds)

The best first run is local and proof-driven. It should work before you connect an API key, proxy, paid model, or enterprise setup.

pip install -U entroly     # or: npm i -g entroly  ·  brew install juyterman1000/entroly/entroly

1. Prove the package works on your machine:

entroly verify-claims      # SDK import, indexing, optimization, exact recovery, engine mode
entroly simulate           # local no-LLM savings estimate on your current repo

2. Pick one integration path:

3. Best setup for Claude Code subscription users:

claude mcp add entroly -- entroly

Claude Code stays your client. Entroly adds local tools for compression, retrieval, receipts, and savings reports.

4. One command — auto-detects your IDE, wraps your agent, opens the dashboard:

cd /your/repo && entroly go

5. Or wrap a specific agent:

entroly wrap claude     # Claude Code
entroly wrap cursor     # Cursor
entroly wrap codex      # Codex CLI
entroly wrap aider      # Aider

6. Or run the proxy — best for pay-as-you-go API keys and custom apps:

entroly proxy                                   # http://localhost:9377
ANTHROPIC_BASE_URL=http://localhost:9377     your-app
OPENAI_BASE_URL=http://localhost:9377/v1     your-app
GOOGLE_GEMINI_BASE_URL=http://localhost:9377/v1beta     your-app

7. Or measure it on your own repo first:

entroly demo            # before/after token + cost estimate
entroly simulate        # local no-LLM savings estimate
entroly perf            # local no-LLM savings + optimizer latency
entroly verify-claims   # runs the packaged self-test, writes a JSON report

Local-first: your code is indexed and selected on-device, never sent anywhere for analysis. Apache-2.0. No outbound analytics by default.

First-run success contract

Entroly should feel useful before you connect a paid model key:

• entroly verify-claims proves SDK import, local indexing, optimization, exact recovery, and native/pure-Python engine mode.
• entroly simulate shows the likely token reduction on your repo without making an LLM call.
• MCP setup works for Claude Code subscription users who do not want proxy/API-key mode.
• Proxy mode is available when you control the provider key and want transparent request optimization.
• npm/WASM is available for Node-first users, but Python remains the fullest CLI/SDK path.

If your repo is tiny or already under budget, Entroly should say so and pass through rather than invent fake savings.

Context Commits

A Context Commit is a portable JSON artifact for the exact context selected for an agent request. It binds the ordered selected text, omitted evidence, exact recovery data, engine/version identity, and optional parent lineage to one content-addressed ctx_... identifier.

entroly context-commit ./repo --query "Where is token rotation enforced?" \
  --budget 8000 --out context-commit.json
entroly context-commit --verify context-commit.json

from entroly import create_context_commit, replay_context, verify_context_commit

commit = create_context_commit(
    [("auth.py", open("auth.py", encoding="utf-8").read())],
    query="Where is token rotation enforced?",
    token_budget=8000,
)
assert verify_context_commit(commit).valid
exact_context = replay_context(commit)

The artifact is self-contained and therefore may contain source text in its recovery bundle. Keep it under the same access and retention policy as the source repository. Content addressing proves mutation, not signer identity; use Entroly's optional Ed25519 attestation and Merkle-log APIs when custody or operator identity matters. Contract and threat model.

Context Receipts

Entroly gives every AI answer a context receipt: what was used, what was omitted, why, and what risks remain. This is built for hard multi-document work such as contracts, policies, addenda, code reviews, and audit evidence where "top-k chunks" is not enough.

entroly ingest ./docs
entroly select --query "Does this contract have a change-of-control clause?" --budget 8000
entroly receipt .entroly/receipts/cr_example.json
entroly audit .entroly/session_chain.json
entroly explain --why-omitted chk_example --receipt .entroly/receipts/cr_example.json

The receipt JSON includes selected chunks, omitted relevant chunks, ranking reasons, dependency links, source fingerprints, token ratio, warnings, and a reproducibility hash. The Markdown report is designed for human review before a compressed context is trusted.

Implementation notes:

• Rust core (entroly-core/src/context_receipts.rs) handles deterministic ingestion, BM25-style ranking, dependency scans, selection, and hashes when the native wheel is available.
• Python control plane (entroly/context_receipts/) provides CLI wiring and a pure-Python fallback for source checkouts.
• The semantic/vector scorer and reranker are explicit extension points; the local MVP ships with lexical scoring and dependency heuristics, not a legal-accuracy guarantee.

Examples:

• Example receipt JSON
• Example Markdown report
• Limitations

Proof

Context Commit conformance (synthetic deterministic code fixtures, local, no model or network calls):

Reproduce: python -m benchmarks.context_commit_conformance. Raw JSON. These numbers measure artifact integrity, replay, and recovery on the committed fixtures; they do not measure model-answer quality or claim identical Python/Rust selection.

Context Efficiency Frontier research: Entroly includes a paired, model-neutral benchmark for the question token-savings tables cannot answer: does less context preserve real task quality? The preregistered protocol compares raw context, model-native compaction, Entroly, and their combination using provider-observed tokens, cost, latency, task success, evidence recall, and unsupported claims.

Read the preregistered protocol. No headline result is claimed until the paired confidence bounds pass.

Every number below is reproducible and backed by a committed JSON artifact you can audit — not a screenshot.

Token savings (this repo, entroly verify-claims, local, no API):

Accuracy retention — does compression hurt answers? Measured with gpt-4o-mini; intervals are Wilson 95% CIs. Each row links its raw result file.

_{*pass-through: context already fit the budget, so Entroly left it unchanged. Reproduce: python benchmarks/run_readme_benchmarks.py (needs OPENAI_API_KEY). Full table + MMLU/TruthfulQA in DETAILS.}

Hallucination guard — HaluEval-QA, standard protocol, GPT-judge baseline on identical data:

_{$0, zero-network verifier that statistically ties a strong LLM judge. Reproduce: python benchmarks/halueval_qa_faithful.py. Proof JSON.}

Works with your stack

OpenClaw: keep the evidence uniform compression drops

The beta OpenClaw context engine scores older messages against the current request. Matching evidence is pinned verbatim when it fits a bounded reserve; lower-value history is compressed around it, and every decision is written to a local receipt.

In the committed synthetic, no-model control below, both strategies fit the same 1,800-token estimated budget. Uniform compression lost the exact old authentication instruction; evidence pinning retained it byte-for-byte.

Reproduce locally: python -m benchmarks.openclaw_evidence_pinning. Benchmark JSON · Plugin setup

_{Synthetic deterministic workload, 23,114 estimated source tokens, 11 messages, zero model calls. Token counts are estimates, not billed usage, and this result does not establish downstream model accuracy.}

entroly wrap <agent> picks the best integration for each tool — proxy env-wrap for CLIs, auto-merged mcp.json for MCP-aware IDEs, or a best-effort endpoint/config hint.

Wrap in one command: claude · cursor · codex · aider · gemini · windsurf · vscode · zed · cline · continue and 28 more.

As a library (LangChain, LlamaIndex, your own code):

from entroly import compress, compress_messages, optimize

compressed = compress(api_response, budget=2000)          # query-agnostic
messages   = compress_messages(messages, budget=30000)    # whole conversation
gentle     = compress_messages(messages, target_ratio=0.90)  # smooth relative operating point
context    = optimize(fragments, budget=8000, query="fix the login bug")  # task-conditioned

compress_messages infers the final user turn as the task and uses it to prioritize answer-relevant evidence in older context. target_ratio is based on Entroly's dependency-free token estimate; measure provider-observed tokens with the Context Efficiency Frontier before publishing a savings claim.

In CI — fail the build if a prompt blows the token budget:

- run: pip install entroly && entroly batch --budget 8000 --fail-over-budget

When to use it · when to skip

Great fit

• Large repos where the agent only sees a few files at a time
• Chatty, multi-turn agents (cache alignment compounds the savings)
• Anywhere you want answers checked against evidence before you trust them
• Teams trying to cut a real, growing AI bill

Skip it (it'll just pass through)

• Tiny repos or short prompts that already fit the budget
• Judgment-heavy tasks where you want the full flagship model every time

What's inside

Most people install Entroly for input-token compression. It actually ships 19 local cost-saving mechanisms across input, inference, output, verification, and learning — each one readable in the source with a committed benchmark where applicable.

pip install entroly            # core: MCP server + Python engine
pip install entroly[proxy]     # + HTTP proxy
pip install entroly[native]    # + Rust engine
pip install entroly[full]      # everything

npm install -g entroly         # WASM runtime, no Python needed
docker pull ghcr.io/juyterman1000/entroly:latest

cd entroly/entroly-core && cargo build --release --bin entroly-rs --features proxy
./target/release/entroly-rs proxy --upstream https://api.anthropic.com

WITNESS — check answers before you trust them

entroly witness --context-file evidence.txt --output-file answer.txt --mode strict
entroly proxy --witness strict --witness-profile rag    # suppress unsupported claims inline

Profiles tune false-positive behavior per workload (rag, qa, code fail closed; chat, summary warn). Every non-streaming response gets a proof certificate; the dashboard shows flagged claims, evidence snippets, and suppression counts. Optional offline DeBERTa NLI (ENTROLY_LOCAL_NLI=1) raises accuracy further at $0.

Why Entroly is different

The winning product is not the one that makes the prompt smallest. It is the one that helps the model do the best work for the fewest tokens.

Entroly is built around that trust contract: select the right evidence, compress supporting material, keep originals recoverable, emit a receipt, and verify the answer against the retained evidence.

The goal is same-quality or better model work at materially lower token cost.

Self-improving local runtime

Entroly has a guarded self-improvement loop. It is designed to learn from real outcomes without letting adaptation run wild.

This is the important distinction: Entroly does not just remember context. It can learn which context-selection strategies, routes, and skills actually produce successful work.

Compared to

Compressing a bad selection is still a bad selection. Entroly ranks first, then compresses — so the model gets structure, not just fewer tokens.

Docs & community

• Architecture & full spec — Rust modules, 3-resolution compression, provenance, RAG comparison, SDK, LangChain.
• Product surface map — CLI, SDK, MCP, proxy, npm/WASM, verification, memory, and security surfaces.
• First-run trust guide — exactly what a new user should run before wiring a paid model.
• For teams — ROI, security, deployment one-pager.
• Limitations — where Entroly helps, where it passes through, and what it does not guarantee.
• Cookbook — copy-paste recipes for common workflows.
• Discord Community · Discussions · Issues

_{Apache-2.0 · local-first · no outbound analytics by default}

pip install entroly && entroly go