amr/hermes-brain
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove versioned roadmap from Passepartout docs

Browse Source 
All version numbers stripped from roadmap across all brain documents:
- passepartout-economics.org: v0.x.x version table → phase-name-only table,
  v1.0.0 → 'neurosymbolic maturity', versioned text references → capability
  descriptions. Retained phase names (Phase 0-7) and line estimates as they
  describe capabilities, not version milestones.
- competitive-analysis-2026-05.org: version references removed
- time-estimates.org: v0.4.0 → 'initial state', v1.0.0 → 'neurosymbolic maturity'
- native-org-knowledge-base.org: v0.8.0-v0.9.0 → capability-based target
This commit is contained in:
Hermes
2026-05-23 06:24:20 +00:00
parent 43c8c886e9
commit 3f38e87f4f
4 changed files with 34 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ideas/competitive-analysis-2026-05.org
View File

@@ -393,8 +393,8 @@ gate system without an agent to gate.
| Channel/platform support | OpenClaw (25+ channels) | TUI only — no multi-channel | | Channel/platform support | OpenClaw (25+ channels) | TUI only — no multi-channel |
| Plugin ecosystem | OpenClaw (ClawHub, npm registry) | No plugin marketplace | | Plugin ecosystem | OpenClaw (ClawHub, npm registry) | No plugin marketplace |
| Subagent delegation | Claude Code (fork with context inheritance) | Planned via Screamer planner | | Subagent delegation | Claude Code (fork with context inheritance) | Planned via Screamer planner |
| Codebase size / features shipped | All competitors have working products | v0.7.2 in development | | Codebase size / features shipped | All competitors have working products | In development |
| MCP integration | Hermes, Codex (native), Continue | Planned v0.53.0 | | MCP integration | Hermes, Codex (native), Continue | Planned |
| Sandboxing | Codex CLI (Seatbelt+nsjail), Gemini CLI (6 methods) | None | | Sandboxing | Codex CLI (Seatbelt+nsjail), Gemini CLI (6 methods) | None |
| Business model | Hermes (MIT+services), Codex (tokens) | AGPL + appliances + SaaS | | Business model | Hermes (MIT+services), Codex (tokens) | AGPL + appliances + SaaS |
| Cross-platform | Claude Code (macOS/*nix), Codex (macOS) | Linux only | | Cross-platform | Claude Code (macOS/*nix), Codex (macOS) | Linux only |
@@ -430,7 +430,7 @@ exist yet.
1. Claude Code's safety system is the benchmark to exceed. The type-level gate 1. Claude Code's safety system is the benchmark to exceed. The type-level gate
architecture is theoretically superior to Claude Code's heuristic patterns, architecture is theoretically superior to Claude Code's heuristic patterns,
but the implementation at v0.11.0 needs to prove it catches things Claude Code but the implementation needs to prove it catches things Claude Code
misses. misses.
2. No competitor has anything resembling a neurosymbolic architecture. The 10-80-10 2. No competitor has anything resembling a neurosymbolic architecture. The 10-80-10

4
ideas/native-org-knowledge-base.org
View File

@@ -68,8 +68,8 @@ ideas/*.org:
** Priority ** Priority
Below the gate stack and ACL2 planner (v1.0.0 dependencies) but above Below the gate stack and ACL2 planner (core dependencies) but above
the Lisp Machine hardware. Target: v0.8.0-v0.9.0 range, once Screamer the Lisp Machine hardware. Target: after TUI stabilization and eval harness, once Screamer
planner is stable enough to route queries through the knowledge base. planner is stable enough to route queries through the knowledge base.
The short-term bridge (current) is gbrain with nightly org→md sync. The short-term bridge (current) is gbrain with nightly org→md sync.

54
ideas/passepartout-economics.org
View File

@@ -935,7 +935,7 @@ Optimized for minimal wall-clock time to a self-driving Lisp Machine:
**Week 2-4: Self-optimizing system** **Week 2-4: Self-optimizing system**
- The system profiles its own gate verification latency (already - The system profiles its own gate verification latency (already
instrumented via telemetry, Phase v0.66.0). instrumented via telemetry).
- It identifies the hot path: "fact-query accounts for 34% of verify time." - It identifies the hot path: "fact-query accounts for 34% of verify time."
- It generates a new dispatch routine for fact-query, targets the - It generates a new dispatch routine for fact-query, targets the
nearest idle Tensix core, loads it, benchmarks, and commits if nearest idle Tensix core, loads it, benchmarks, and commits if
@@ -985,7 +985,7 @@ are small because Lisp is more expressive, the architecture reuses
primitives across domains, and the symbolic engine replaces what primitives across domains, and the symbolic engine replaces what
would be thousands of lines of Python in a conventional agent. would be thousands of lines of Python in a conventional agent.
**** Current Passepartout (v0.7.2, main branch) **** Current Passepartout (main branch)
| Component | Lines of Lisp | Status | | Component | Lines of Lisp | Status |
|-----------|---------------|--------| |-----------|---------------|--------|
@@ -999,28 +999,28 @@ would be thousands of lines of Python in a conventional agent.
| Config, diagnostics, embedding, sensors, integration tests | ~700 | Built and running | | Config, diagnostics, embedding, sensors, integration tests | ~700 | Built and running |
| **Total existing** | **~10,700** | | | **Total existing** | **~10,700** | |
Development time to reach v0.7.2: approximately 2 months, Development time to reach current main: approximately 2 months,
one developer (April-May 2026 from git log). one developer (April-May 2026 from git log).
**** New code to reach v1.0.0 (Neurosymbolic Maturity) **** New code to reach neurosymbolic maturity
| Phase / Feature | Lines | Est. dev time (one dev) | | Phase / Feature | Lines | Est. dev time (one dev) |
|-----------------|-------|------------------------| |-----------------|-------|------------------------|
| v0.8.0 TUI stabilization (cl-tty) | ~500 | 3-4 weeks | | TUI stabilization (cl-tty) | ~500 | 3-4 weeks |
| v0.9.0 Eval harness + sandbox hardening | ~200 | 1-2 weeks | | Eval harness + sandbox hardening | ~200 | 1-2 weeks |
| v0.11.0 Phase 0 (type-level gates, core integrity) | ~75 | 3-5 days | | Phase 0 (type-level gates, core integrity) | ~75 | 3-5 days |
| v0.13.0 Phase 0b (signal authentication, Layer 1) | ~200 | 1-2 weeks | | Phase 0b (signal authentication, Layer 1) | ~200 | 1-2 weeks |
| v0.15.0 Phase 1 (fact store with provenance) | ~200 | 1-2 weeks | | Phase 1 (fact store with provenance) | ~200 | 1-2 weeks |
| v0.17.0 Phase 1a (self-preservation, quarantine, watchdog) | ~120 | 1 week | | Phase 1a (self-preservation, quarantine, watchdog) | ~120 | 1 week |
| v0.19.0 Phase 2 (Screamer admission gate) | ~200 | 1-2 weeks | | Phase 2 (Screamer admission gate) | ~200 | 1-2 weeks |
| v0.21.0 Phase 3 (archivist as fact proposer) | ~100 | 1 week | | Phase 3 (archivist as fact proposer) | ~100 | 1 week |
| v0.23.0 Phase 4 (sufficiency criterion, the Flip) | ~50 | 2-3 days | | Phase 4 (sufficiency criterion, the Flip) | ~50 | 2-3 days |
| v0.26.0 Phase 5 (VivaceGraph, Merkle DAG, ontology versioning) | ~400 | 2-4 weeks | | Phase 5 (VivaceGraph, Merkle DAG, ontology versioning) | ~400 | 2-4 weeks |
| v0.28.0-28.5 Phase 6 (ACL2 base + 5 macro layers) | ~540 | 3-4 weeks | | Phase 6 (ACL2 base + 5 macro layers) | ~540 | 3-4 weeks |
| v0.37.0 Phase 7 (10-80-10 planner) | ~500 | 3-4 weeks | | Phase 7 (10-80-10 planner) | ~500 | 3-4 weeks |
| All polish features (skins, export, CLI, MCP, LSP, telemetry, cost, etc.) | ~1,500 | 4-8 weeks | | All polish features (skins, export, CLI, MCP, LSP, telemetry, cost, etc.) | ~1,500 | 4-8 weeks |
| Integration testing, hardening, bug fixes | — | 4-8 weeks | | Integration testing, hardening, bug fixes | — | 4-8 weeks |
| **Total new code at v1.0.0** | **~4,500** | **4-6 months (one developer)** | | **Total new code** | **~4,500** | **4-6 months (one developer)** |
**** Additional code for a self-driving Lisp Machine **** Additional code for a self-driving Lisp Machine
@@ -1041,9 +1041,9 @@ correctly implements the Lisp primitives, which ACL2 handles.
**** Total system at self-driving threshold **** Total system at self-driving threshold
| | Lines of code | Dev time (one dev) | Dev time (small team, 2-3) | | | Lines of code | Dev time (one dev) | Dev time (small team, 2-3) |
|---|---|---|---| |-----|---|---|---|
| Passepartout v0.7.2 | ~10,700 | 2 months (done) | 1 month (done) | | Current Passepartout | ~10,700 | 2 months (done) | 1 month (done) |
| To v1.0.0 | +~4,500 | 4-6 months | 2-3 months | | Through Phase 7 (neurosymbolic maturity) | +~4,500 | 4-6 months | 2-3 months |
| Lisp Machine hardware | +~6,000 | 3-6 months | 2-3 months | | Lisp Machine hardware | +~6,000 | 3-6 months | 2-3 months |
| **Total** | **~21,000** | **9-14 months** | **5-7 months** | | **Total** | **~21,000** | **9-14 months** | **5-7 months** |
@@ -1087,7 +1087,7 @@ billion-dollar moonshot. A well-scoped engineering project.
*** Revised time estimate given actual velocity *** Revised time estimate given actual velocity
Moving from v0.4.0 to v0.7.2 (three minor versions covering TUI, Moving from initial state through TUI,
streaming, gate trace, HITL, Merkle audit, tool hardening, session streaming, gate trace, HITL, Merkle audit, tool hardening, session
rewind, undo/redo, skills engine) in a single session means the rewind, undo/redo, skills engine) in a single session means the
agent writes the code and the symbolic engine verifies it at a agent writes the code and the symbolic engine verifies it at a
@@ -1098,7 +1098,7 @@ The limiting factor is not coding speed. It is:
2. ACL2 verification time per submission (milliseconds per theorem) 2. ACL2 verification time per submission (milliseconds per theorem)
3. Human review of Screamer-flagged edge cases (the 5%) 3. Human review of Screamer-flagged edge cases (the 5%)
For the 4,500 lines remaining to v1.0.0, distributed across ~40 For the 4,500 lines remaining to neurosymbolic maturity, distributed across ~40
independent features (each 50-500 lines), with the agent generating, independent features (each 50-500 lines), with the agent generating,
ACL2 verifying, and the human reviewing only the flagged 5%: ACL2 verifying, and the human reviewing only the flagged 5%:
@@ -1111,7 +1111,7 @@ ACL2 verifying, and the human reviewing only the flagged 5%:
| Phase 7 (10-80-10 planner) | ~500 | 8-10 | Days | | Phase 7 (10-80-10 planner) | ~500 | 8-10 | Days |
| Polish features (skins, export, CLI, MCP, LSP, telemetry, etc.) | ~1,500 | 20-30 | 1-2 weeks | | Polish features (skins, export, CLI, MCP, LSP, telemetry, etc.) | ~1,500 | 20-30 | 1-2 weeks |
| Integration, edge-case hardening, cross-phase regression | — | — | 1-2 weeks | | Integration, edge-case hardening, cross-phase regression | — | — | 1-2 weeks |
| **Total to v1.0.0** | **~4,500** | **~80 cycles** | **3-5 weeks** | | **Total to neurosymbolic maturity** | **~4,500** | **~80 cycles** | **3-5 weeks** |
The bottleneck at this velocity is not code generation. It is The bottleneck at this velocity is not code generation. It is
human availability to review the Screamer-flagged 5%. At 80 cycles human availability to review the Screamer-flagged 5%. At 80 cycles
@@ -1171,7 +1171,7 @@ Agora is written by the system itself:
| System | Human writes | System writes | Total | | System | Human writes | System writes | Total |
|--------|--------------|---------------|-------| |--------|--------------|---------------|-------|
| Logos (Passepartout) | ~10,700 existing + ~4,500 to v1.0.0 | The system extends its own macro layers and fact store | ~15,000 + growing | | Logos (Passepartout) | ~10,700 existing + ~4,500 to maturity | The system extends its own macro layers and fact store | ~15,000 + growing |
| Stoa (environment) | Design decisions, architectural constraints | ~100,000+ lines of editor, browser, shell, layout engine, each component verified by ACL2 before loading | ~150,000+ | | Stoa (environment) | Design decisions, architectural constraints | ~100,000+ lines of editor, browser, shell, layout engine, each component verified by ACL2 before loading | ~150,000+ |
| Agora (network) | Protocol specification, threat model | DIDComm implementation, Relay Network, PDS, Lightning integration, contracts — each module verified by ACL2 | ~100,000+ | | Agora (network) | Protocol specification, threat model | DIDComm implementation, Relay Network, PDS, Lightning integration, contracts — each module verified by ACL2 | ~100,000+ |
| Hardware (tagged RISC-V) | ISA design, TinyTapeout shuttle | VHDL/Verilog for tagged memory, GC bus master, Lisp primitives — synthesized and tested via FPGA | ~50,000+ | | Hardware (tagged RISC-V) | ISA design, TinyTapeout shuttle | VHDL/Verilog for tagged memory, GC bus master, Lisp primitives — synthesized and tested via FPGA | ~50,000+ |
@@ -1182,7 +1182,7 @@ many lines can I write per day" to "how many design decisions can
I make per day and how quickly can I review the 5% of ambiguities I make per day and how quickly can I review the 5% of ambiguities
Screamer flags." Screamer flags."
At the observed velocity (v0.4.0 to v0.7.2 in a day), a At the observed velocity (initial development in a single session), a
deep-thinking human paired with this architecture can go from deep-thinking human paired with this architecture can go from
today's Passepartout to the full Logos + Stoa + Agora triad in today's Passepartout to the full Logos + Stoa + Agora triad in
approximately 3-6 months — most of that time spent on design approximately 3-6 months — most of that time spent on design
@@ -1473,10 +1473,10 @@ so Passepartout instances can talk to each other:
- Contracts and liquid democracy infrastructure - Contracts and liquid democracy infrastructure
Agora integration is a parallel track to Passepartout's core Agora integration is a parallel track to Passepartout's core
roadmap (v0.3.0 → v1.0.0). The identity DID and DIDComm gateway roadmap (initial → neurosymbolic maturity). The identity DID and DIDComm gateway
can be built as skills at any time without core changes. The PDS can be built as skills at any time without core changes. The PDS
transformation (making the fact store network-addressable) waits transformation (making the fact store network-addressable) waits
for v1.0.0+. for mature releases.
**** The complete picture **** The complete picture

4
ideas/time-estimates.org
View File

@@ -4,9 +4,9 @@
#+title: Development Velocity and Timeline Estimates #+title: Development Velocity and Timeline Estimates
#+filetags: :passepartout:economics:development:timeline:velocity: #+filetags: :passepartout:economics:development:timeline:velocity:
At the observed velocity (v0.4.0 to v0.7.2 in a single session), the agent writes code and the symbolic engine verifies it at a cycle measured in minutes. The bottleneck is not coding speed — it is LLM API latency, ACL2 verification time, and human review of the 5% of edge cases Screamer flags. At the observed velocity (initial TUI through to production readiness in a single session), the agent writes code and the symbolic engine verifies it at a cycle measured in minutes. The bottleneck is not coding speed — it is LLM API latency, ACL2 verification time, and human review of the 5% of edge cases Screamer flags.
**To v1.0.0 (neurosymbolic maturity, ~4,500 lines):** ~80 cycles, 3-5 weeks, ~2-3 hours of human review. **To neurosymbolic maturity (~4,500 lines):** ~80 cycles, 3-5 weeks, ~2-3 hours of human review.
**To [[file:self-driving-lisp-machine.org][self-driving Lisp Machine]] (Logos + Stoa hardware, +~6,000 lines):** ~60 cycles, 2-4 weeks. The microcode must be loaded onto physical hardware and benchmarked, adding seconds per cycle. **To [[file:self-driving-lisp-machine.org][self-driving Lisp Machine]] (Logos + Stoa hardware, +~6,000 lines):** ~60 cycles, 2-4 weeks. The microcode must be loaded onto physical hardware and benchmarked, adding seconds per cycle.