English · 中文
Governed capability standards for agent-callable software · schema-enforced modules · protocol-neutral execution boundaries
I work on the boundary where an agent stops reasoning and starts causing things to happen.
MCP tells an agent what it can call. apcore decides whether this call — with these arguments, in this environment, by this identity — should happen at all, and leaves evidence that it did.
Most of the agent-tooling stack today is a discovery problem solved twice and an authorization problem solved zero times. A tool schema tells a model how to format a call. It says nothing about who may make it, what it may touch, whether a human must approve it first, or what record survives afterwards. Those questions do not belong in the model's reasoning loop — they belong at the execution boundary, enforced identically no matter which protocol carried the request.
That is the position apcore takes:
┌──────────────────────────────────────────┐
│ Agent · Human · Application │
└────────────────────┬─────────────────────┘
│
┌──────────┬──────────┬──────┴────┬──────────┬──────────┐
▼ ▼ ▼ ▼ ▼ ▼
┌─────┐ ┌───────┐ ┌───────┐ ┌──────┐ ┌───────┐ ┌────────┐
│ MCP │ │ A2A │ │ CLI │ │ HTTP │ │OpenAI │ │ direct │
└──┬──┘ └───┬───┘ └───┬───┘ └──┬───┘ └───┬───┘ └───┬────┘
└──────────┴──────────┴─────┬────┴───────────┴──────────┘
▼
╔═══════════════════════════════════════════════╗
║ apcore runtime ║
║ schema · ACL · approval gate · middleware ║
║ observability · audit trail ║
╚═══════════════════════┬═══════════════════════╝
▼
┌──────────────────────────────────────────┐
│ your existing business logic │
│ (unchanged) │
└──────────────────────────────────────────┘
Define a governed capability once. Expose it through any surface. The guarantees do not change when the transport does.
Everything below lives under @aiperceivable.
Core standard — a protocol specification with three independent implementations, held together by cross-language conformance fixtures rather than by a shared codebase. Full documentation →
| Repository | Install | |
|---|---|---|
| Specification | apcore | — |
| Python | apcore-python | pip install apcore |
| TypeScript | apcore-typescript | npm install apcore-js |
| Rust | apcore-rust | cargo add apcore |
Surface adapters — the same module, projected onto a different protocol. Each is specified once and implemented three times, with a shared conformance suite pinning the behavior that must match.
| Surface | Spec | Python | TypeScript | Rust |
|---|---|---|---|---|
| Model Context Protocol | apcore-mcp | py | ts | rs |
| Agent2Agent | apcore-a2a | py | ts | rs |
| Command line | apcore-cli | py | ts | rs |
Meeting code where it already is — integrations that scan an existing codebase and expose what is already there, rather than asking anyone to rewrite it.
fastapi-apcore · django-apcore · flask-apcore · nestjs-apcore · axum-apcore · tiptap-apcore
And for the code that has no framework at all — apexe wraps an existing CLI binary into a governed module by scanning its help output, so a forty-year-old tool arrives at an agent with the same ACL and approval semantics as a hand-written one.
Orchestration — apflow, distributed task orchestration where every capability in the graph is itself an apcore module.
Separately, a set of Claude Code skills for the parts of engineering that reward a checklist over improvisation:
| code-forge | TDD-driven implementation — plan, execute, debug, review, worktree and branch lifecycle, parallel agent dispatch |
| spec-forge | PRD, SRS, technical design, and test plans — standalone, or as one traceability chain |
| theory-forge | Academic rigor auditing — citation truth, falsifiability, Toulmin argument structure, scope discipline, counter-argument engagement |
| research-forge | Technical and business due diligence on open-source projects and products |
| prompt-coach | Real-time prompt and target-language coaching, as a UserPromptSubmit hook |
| agent-skill-bundler | Port Claude Code skills to other agent platforms |
| tercel-claude-plugins | The marketplace that ships them |
aiperceivable.com · @tercelyi · LinkedIn
Issues and design discussions are welcome on any repository above — particularly the hard parts: authorization semantics, cross-language conformance, and what an agent is entitled to assume when a call comes back denied.