CORE is a cognitive harness paradigm for coding agents, developed as part of the broader open source research at Ori Mnemos on modeling human cognition in language model systems in a manner similar to how a plane models a bird.
Agents should not reason through bash.
The Core Thesis
Bash is an unstructured string interface with no object model, no composable namespace, and no capacity for recursive dispatch.
Language models reason natively through structured token generation — composing expressions, operating on typed objects, building outputs from intermediate results. Bash breaks this at every serialization boundary; a REPL environment preserves it richly.
CORE transforms the codebase into a knowledge graph and exposes that graph as a Python REPL environment the agent can natively traverse.
A New Execution Environment
Inside this environment, the agent writes Python that composes operations in a single turn:
- Search the graph
- Cluster results by file
- Fan out to fresh LLM sub-reasoners per cluster via
rlm_callandrlm_batch - Synthesize the outputs
One expression replaces what tool-calling architectures require ten or more sequential round-trips to accomplish.
Recursion as the Primitive
Recursive language model calls are the core primitive.
A language model, mid-reasoning, spawning focused instances of itself on decomposed sub-problems and composing the results back into a unified output.
Recursion applied to inference.
Why This Outperforms Bash
Bash requires the agent to:
- Serialize every operation into a string command
- Wait for unstructured output
- Parse that output back into something meaningful
- Decide the next command
Each step is a lossy boundary. Structure is destroyed on the way out and reconstructed — if at all — on the way back in.
At Scale
THE BASH PROBLEM
Ten sequential tool calls.
Ten serialization boundaries. Ten parse attempts. Ten opportunities to misinterpret output or lose context.
Eliminating the Boundary
CORE eliminates these boundaries entirely.
The agent operates on structured objects:
- Graph nodes with PageRank scores
- Clustered search results
- Typed function returns
Nothing is serialized into strings. Nothing is parsed back.
The codebase is not queried from outside through a shell — it is navigated from within as a first-class data structure.
The codebase is not queried from outside. It is navigated from within.