Implicit Core MCP server
Commit Oct 16, 2026Virtualize large agent environments by materializing only the specific state required for each interaction to reduce memory and storage overhead.
Also known as zeitcow/implicit-core, implicit-core
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Oct 16, 2026
- License
- Apache-2.0
What is Implicit Core MCP?
Implicit Core is an MCP server. Virtualize large agent environments by materializing only the specific state required for each interaction to reduce memory and storage overhead.
Summary generated from the project's README
About Implicit Core MCP server
Virtualizing large agent environments by materializing only the specific state required for each interaction is what Implicit Core enables for AI developers. It reduces memory and storage overhead by addressing specific coordinates in a versioned environment rather than constructing a complete environment for every episode. This is particularly useful for training and evaluation scenarios where the total possible environment, such as a warehouse with millions of orders, is much larger than any single interaction.
Developers use this infrastructure by building adapters with Python protocols to load required pages on demand. The system works at the logical environment-state layer and can integrate with existing agents, learners, and evaluators. For those using coding agents like Claude Code, Cursor, or VS Code, the package provides eight bounded local stdio MCP tools for synthetic addressing, paging, provenance, and validation. The setup requires Python 3.11+ and can be installed via pip using the implicit-ai distribution.
What you can do with it
- 1Reduce environment storage overheadA developer can minimize the bytes needed to store agent states by only materializing the specific data required for an interaction.
- 2Enable reproducible agent episodesYou can ensure repeatable agent behavior by using immutable source versions and fixed seeds within the environment.
- 3Connect coding agents to virtualized statesIntegrate tools like Cursor or Claude Code to manage synthetic addressing and provenance through MCP.
- 4Manage massive scale environmentsHandle environments that are too large to load entirely, such as a warehouse containing millions of orders.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablezeitcow/implicit-core is public and reachablegithub.com/zeitcow/implicit-core ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-16github.com/zeitcow/implicit-core ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubImplicit Core
Implicit is the experience layer for AI agents.
Virtualize large agent environments. Materialize only the state each experience actually needs.
Implicit Core is AI agent experience/environment infrastructure from zeitcow/implicit-core, distributed as implicit-ai under Apache-2.0. Current stable: 1.0.1.
pip install implicit-ai
Website and docs · PyPI · 60-second quickstart · Measured evidence · Connect a coding agent · Install the Codex integration skill
Why virtualize an experience?
In agent training and evaluation, the possible environment can be much larger than any individual episode. A warehouse may contain millions of orders; processing one order needs only its inventory and policy records. Instead of eagerly constructing the complete environment for every episode, an Implicit experience addresses a coordinate in a versioned environment. Your adapter supplies the initial pages and loads further required state on demand, including declared dependencies.
An experience is one addressable interaction: instruction, required state, execution and evaluation. The address identifies the environment version and coordinate. Your adapter chooses pages; your existing agent executes; your native evaluator verifies the result. Core records execution state, provenance and explicit recovery.
Immutable source versions, fixed seeds and deterministic adapters, state sources and agents support reproducible episodes. External services and effects need application-owned control or reconciliation; Implicit does not make arbitrary programs deterministic. Architecture explains the conditions.
This works at the logical experience/environment-state layer. VM or container snapshots can supply an execution sandbox; Implicit determines which addressed state is needed inside an experience. FAQ distinguishes this from filesystem paging, dataset streaming, prompt compression and lazy MCP tool discovery.
Use Implicit for large separable state, repeatable identities, expensive environment construction or durable execution evidence. Measure overhead for small, already lazy or mostly accessed environments.
Try it in 60 seconds
Python 3.11+; zero third-party runtime dependencies. In a fresh virtual environment:
pip install implicit-ai
implicit --version
implicit demo
implicit benchmark
The public toy compares eager and selective serialized state, verifies the shipping result and prints a provenance hash. Its output is its own workload measurement.
The distribution is implicit-ai; the import is implicit. Use an isolated environment because the unrelated implicit recommendation library shares that import namespace. Installation includes Windows setup and verified release artifacts.
Measured evidence and its limits
In the preserved rc1 native systems population, 155/155 comparable cases preserved equivalent state, tool behavior and reward.
| Measurement | Result |
|---|---|
| Aggregate retained serialized/materialized-state reduction | 93.88% |
| Mean case reduction | 94.40% |
| Median case reduction | 99.55% |
Serialized/materialized bytes are not RAM. The measurements belong to rc1, not a new 1.0.0 native replay or the toy/MCP demo. The public numeric summary supports arithmetic verification; restricted native replay assets are not shipped. Methodology, measured latency tradeoffs, hashes and limitations.
Keep your existing stack
Keep your agent, learner, framework and evaluator. Build an adapter in your project using ordinary Python protocols:
Universe proposes versioned addresses
-> Environment plans required pages
-> ResourceSource loads pages as needed
-> existing agent executes
-> native Evaluator verifies
-> Core records provenance and recovery state
Adapter contract, agent integration prompts and three public adapter shapes show the mapping. With the public repository downloaded and the package installed:
python -I examples/core_adapters.py
No allocator or new learner is required. Default selection preserves your proposed order. Core does not establish improved learning, general speedups, allocator superiority or universal infrastructure guarantees.
Let a coding agent try Implicit
The package includes eight bounded local stdio MCP tools for synthetic addressing, paging, provenance and validation. MCP quickstart gives Codex, Claude Code, VS Code and Cursor configurations. Real environment adapters use the Python SDK.
Repository plugin packages integration guidance and local MCP configuration. Public directory acceptance and hosted ChatGPT connectivity are separate; see the dated ecosystem status.
Documentation
- Quickstart, installation and architecture
- Adapters, configuration and agent integration
- Benchmarks, citation guide and FAQ
- Local MCP, MCP quickstart and ecosystem status
- Security and privacy, troubleshooting and contributing
- Agent commands, release history and public adoption measurement
Demo, benchmark and local MCP make no outbound connections. Python adapters are trusted application code and may use your services. There is no product telemetry. Journals may retain application data; see SECURITY.md.
Implicit Core 1.0.1 is licensed under Apache-2.0. Licensing inventory and NOTICE describe included assets.
Implicit Core MCP questions
What is Implicit Core used for?
It is an experience layer for AI agents that allows for the virtualization of large environments by materializing only the state needed for specific experiences.
Does the local MCP implementation make outbound connections?
No, the demo, benchmark, and local MCP tools do not make any outbound connections.
How much state reduction can be achieved?
In tested native systems, the aggregate retained serialized/materialized-state reduction was approximately 93.88%.