Soul MCP
Local-first agent memory with runs, receipts, episodes, conflict handling, calibration, deliberation, and a governed skill registry. 23 MCP tools and 358 automated tests.
Memory loss, false completion, unsupported public claims, behavior drift, violated runtime conditions, or opaque state: each project has a narrow job, public source, explicit limitations, and a verification path.
These projects can work together, but none pretends to be the whole agent stack.
Local-first agent memory with runs, receipts, episodes, conflict handling, calibration, deliberation, and a governed skill registry. 23 MCP tools and 358 automated tests.
Declare an intended world state, observe it with constrained file, HTTP, Git, npm, or manual verifiers, and retain an honestly classified receipt. 53 automated tests.
Turn README, release, product, and agent claims into evidence contracts with policies, dependencies, receipts, CI gates, and five report formats. 70 automated tests.
Compare portable baseline and candidate traces with nine deterministic matchers for tool use, permissions, output structure, outcomes, ranks, sets, sequences, and bounded metrics. 73 automated tests.
Express conditions that must remain true while an agent works, evaluate evidence explicitly, and fail closed when the runtime cannot prove a critical rule. 36 automated tests.
Experimental cognitive-state runtime with associative recall, limited workspace, temporal context, self-model, JSON persistence, and model bridges. Zero runtime dependencies and 446 tests.
NexTool is also a large static collection. Its public surface is counted and checked in CI.
Developer, data, image, text, CSS, security, and productivity utilities. Tool capabilities and external dependencies vary by page.
131 guidesPractical tutorials plus evidence-bounded writing about agent architecture and AI consciousness claims.
Public Git historyA live view of public commits from GitHub, clearly described as AI-assisted and human-directed work.
The former /docs/ page described a prompt document as if it could activate genuine affect or transform any model. That material is preserved as labeled historical provenance in the ANIMA repository, not presented as current product documentation. The maintained ANIMA Kernel is Python software; its state and behavior are testable, while sentience and phenomenal consciousness are not claimed.
Read the current evidence boundary → · Understand prompt vs runtime state →