Agentic Systems

Coverage of external agentic systems and harnesses: execution loops, orchestration, scheduling, permissioning, memory, knowledge, and context. Memory comparisons now consume the main analysis's retained results; see comparison inputs and builds. The companion agent-memory-systems collection retains legacy reviews and historical comparison snapshots.

Analyses

  • Academic Research Skills — Claude Code research pipeline whose prompt-defined stages are supported by narrow executable checks, while orchestration, Passport resume, and terminal gate behavior remain host-dependent or internally conflicted
  • AI Agents in Depth — whole-book comparison whose Model–Harness, context, evaluation, continual-evolution, and coordination doctrine largely converges with Commonplace, while memory admission, evaluator policy, authority granularity, and several evidence claims diverge
  • Autogenesis — self-evolving agent framework whose paper-aligned release exposes versioned protocol resources and an explicit planning bus, while current main replaces them with an expanded extension taxonomy and uniform capability loop; substantial code, but incomplete experiment reproduction and a broken advertised test baseline
  • Eigenius — typed execution and verification substrate with a manually loaded host-agent reasoning protocol: curated MCP, checked justification certificates on named load paths, incomplete recovery/provenance, and conditional Lean correspondence
  • Claude Code dynamic workflows — model-authored orchestrator scripts over sub-agents: the first shipped harness exposure of the bounded call beneath the frozen tool loop, mapped onto the tool-loop cluster
  • Compound Engineering plugin — artifact-mediated software factory whose project-knowledge and optimization loops provide search, evaluation, and retention, but whose installed prompt corpus remains outside the ordinary update loop
  • Fractal — terminal/headless RLM harness over PredictRLM: SBX-mounted workspace turns, model-authored code and sub-model calls, agent-delegation skill, and session continuity stored outside the repo
  • GBrain as an agentic system — the agent-OS half of a popular "memory" project: host-agent adoption protocol, dream-cycle scheduler, durable crash-resumable subagent queue, fail-closed trust boundary, and a gated self-modification loop; memory subsystem reviewed in agent-memory-systems
  • Exo — a harness built for recursive self-improvement: a protected Rust substrate under a fully rewritable executor, allowlisted host control for build and restart, and a sandbox rewind that preserves the record of what was already tried; memory subsystem reviewed in agent-memory-systems
  • Semantic Engine as ingest infrastructure — not an agent-memory system, but a code-grounded ingest workbench: local SQLite staging, source chunking, embeddings, query, and exploratory visualization before KB promotion

Complete file listing (generated at build time)