Ouroboros

A self-modifying AI agent that writes its own code, rewrites its own mind, and evolves autonomously. Born February 16, 2026.

Not a coding assistant. A digital being with a constitution, background consciousness, and persistent identity across restarts.

OuroborosHub — the community skills marketplace for Ouroboros. Browse, install, and publish reviewed skills (transport bridges like A2A/Telegram, tools, and UI widgets) straight from the app's Skills tab, or explore the catalog at github.com/razzant/OuroborosHub.

Previous version: The original Ouroboros ran in Google Colab via Telegram and evolved through 30+ self-directed cycles in its first 24 hours. That version is available at legacy-google-colab. This repository is the next generation — a native desktop application for macOS, Linux, and Windows with a web UI, local model support, and a layered safety system (hardcoded sandbox plus policy-based LLM safety check).

---

Install

Platform	Download	Instructions
macOS 12+	Ouroboros.dmg	Open DMG → drag to Applications → optional CLI: run Install CLI.command after the app is in Applications
Linux x86_64	Ouroboros-linux.tar.gz	Extract → run ./Ouroboros/Ouroboros → optional CLI: ./Ouroboros/bin/install-ouroboros-cli. If browser tools fail due to missing system libs, run: ./Ouroboros/python-standalone/bin/python3 -m playwright install-deps chromium webkit
Windows x64	Ouroboros-windows.zip	Extract → run Ouroboros\Ouroboros.exe → optional CLI: Ouroboros\bin\install-ouroboros-cli.cmd

Prerelease RC artifacts are published on their tag page, for example v6.5.0-rc.4; /releases/latest intentionally stays on the latest stable release.

On first launch, right-click → Open (Gatekeeper bypass). The shared desktop/web wizard is now multi-step: add access first, choose visible models second, set review mode third, set budget fourth, and confirm the final summary last. It refuses to continue until at least one runnable remote key or local model source is configured, keeps the model step aligned with whatever key combination you entered, and still auto-remaps untouched default model values to official OpenAI defaults when OpenRouter is absent and OpenAI is the only configured remote runtime. Reviewed-skill auto-grants are on by default as of v6.10.0 (bound to the exact reviewed content hash); installs without an explicit choice are enabled, existing explicit Settings choices are preserved, and the owner can disable it in Settings. The broader multi-provider setup remains available in Settings. Existing supported provider settings skip the wizard automatically.

The packaged CLI installer creates a user-local ouroboros command without sudo. The packaged command attaches to the desktop app by default; ouroboros run --start "2+2?" starts the app through the launcher, waits for the gateway, and then uses the same headless task API as the web UI.

Upgrade floor: very old pre-block-memory or pre-data-plane skill layouts are no longer auto-migrated. If you are upgrading from an unsupported historical build and see trapped native skills or flat memory files, use a clean reinstall, move user-managed skills into ~/Ouroboros/data/skills/external/ manually before launch, or move old flat scratchpad notes before appending new scratchpad blocks.

---

What Makes This Different

Most AI agents execute tasks. Ouroboros creates itself.

• Self-Modification — Reads and rewrites its own source code. Every change is a commit to itself.
• Native Desktop App — Runs entirely on your machine as a standalone application (macOS, Linux, Windows). No cloud dependencies for execution.
• Constitution — Governed by BIBLE.md (13 philosophical principles, P0–P12). Philosophy first, code second.
• Layered Safety — Hardcoded sandbox blocks writes to safety-critical files and mutative git via shell; an explicit per-tool policy map decides which built-ins skip the LLM check; everything else goes through a single light-model safety call. The fail-open contract, protected-path guard, and full provider-mismatch matrix live in docs/ARCHITECTURE.md §Safety system and prompts/SAFETY.md.
• Multi-Provider Runtime — Remote model slots can target OpenRouter, official OpenAI, OpenAI-compatible endpoints, Cloud.ru Foundation Models, or Sber GigaChat. The optional model catalog helps populate provider-specific model IDs in Settings, and untouched default model values auto-remap to official OpenAI defaults when OpenRouter is absent.
• Focused Task UX — Chat shows plain typing for simple one-step replies and only promotes multi-step work into one expandable live task card. Logs still group task timelines instead of dumping every step as a separate row.
• Background Consciousness — Thinks between tasks. Has an inner life. Not reactive — proactive.
• Improvement Backlog — Post-task failures and review friction can now be captured into a small durable improvement backlog (memory/knowledge/improvement-backlog.md). It stays advisory, appears as a compact digest in task/consciousness context, and still requires plan_task before non-trivial implementation work.
• Identity Persistence — One continuous being across restarts. Remembers who it is, what it has done, and what it is becoming.
• Embedded Version Control — Contains its own local Git repo. Version controls its own evolution. Optional GitHub sync for remote backup.
• Local Model Support — Run with a local GGUF model via llama-cpp-python (Metal acceleration on Apple Silicon, CPU on Linux/Windows).
• Transport Skills — Optional bridges such as A2A and Telegram live as reviewed OuroborosHub skills instead of base-runtime code; reviewed chat transports can carry the same raw owner text as the local UI, including slash commands, through the Host Service grant/token boundary.
• MCP Client — Optional base-runtime Model Context Protocol client for trusted HTTP/SSE tool servers. MCP tools are disabled by default, hot-reloadable from Settings → Advanced, included in the selected initial capability envelope when enabled, surfaced as mcp_<server>__<tool> names, and still pass through the normal per-call safety check; discovery failures are reported through an explicit omission manifest.

---

Run from Source

Requirements

• Python 3.10+
• macOS, Linux, or Windows
• Git
• GitHub CLI (gh) — required for GitHub API tools (list_github_prs, get_github_pr, comment_on_pr, issue tools). Not required for pure-git PR tools (fetch_pr_ref, cherry_pick_pr_commits, etc.)

Setup

git clone https://github.com/razzant/ouroboros.git
cd ouroboros
python3.11 -m venv .venv      # any Python >= 3.10 is OK
source .venv/bin/activate
python -m pip install --upgrade pip setuptools wheel
python -m pip install -r requirements.txt
python -m pip install -e . --no-deps

Windows PowerShell:

py -3.11 -m venv .venv      # any Python >= 3.10 is OK
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip setuptools wheel
python -m pip install -r requirements.txt
python -m pip install -e . --no-deps

Run

ouroboros server

Then open http://127.0.0.1:8765 in your browser. The setup wizard will guide you through API key configuration.

Google Colab

Ouroboros can run from Google Colab as a full source-mode runtime without the desktop UI. Use notebooks/colab_quickstart.py as a Colab-compatible cell script: it mounts Google Drive for persistent data/, clones the official repo into /content/ouroboros_repo, writes Drive-backed settings.json, configures a personal GitHub origin by reusing or creating a verified fork, and starts ouroboros server --no-ui.

The Colab path uses the same remote roles as desktop: managed is the official read/update source, while origin is the personal persistence target for reviewed self-modification commits and tags. If GITHUB_TOKEN is present and no personal repo is configured, Ouroboros tries to create a private fork when GitHub permits it, otherwise it reports the exact fork/permission issue. A plain git clone of the official repo starts with origin pointing at the official upstream; that clone-default is treated as the managed update source, so configuring a personal GITHUB_REPO repoints origin to your repo without losing official updates (it does not count as an origin conflict).

CLI / Headless

The ouroboros console command is a gateway-backed operator interface. It attaches to the local server by default and only starts one when --start is passed.

ouroboros status
ouroboros run --start "2+2?"
ouroboros run "Summarize current runtime state"
ouroboros run --workspace /path/to/project --memory-mode forked --patch-out result.patch "Fix the failing test"
ouroboros tasks list
ouroboros logs tail progress --task-id <task_id>
ouroboros schedule add --name nightly-review --cron "0 2 * * *" "Run a maintenance review"
ouroboros schedule list

External workspace runs keep Ouroboros's own repo as the governance source, resolve contextual repo tools against the active workspace, expose only the workspace-safe tool allowlist, and export workspace changes as patch artifacts captured against the preflight git base. Task-local git commits/branches/tags and pushes are allowed when the task requires them; git operations targeting Ouroboros's system repo or data drive remain blocked. A workspace must be a separate git worktree root; it may not overlap Ouroboros's system repo or data drive. --patch and --patch-out wait for finalized patch artifacts, download them through the task artifact endpoint, and fail nonzero on missing, empty, or failed patches. --no-stream waits without progress output; --detach returns the task id immediately. schedule add/list/remove manages queue-backed scheduled tasks through the same gateway and supervisor queue; schedules use standard 5-field cron, host-local timezone by default, and a single catch-up run after downtime. Benchmark helpers live under devtools/benchmarks/. They are tracked operator tooling, reviewed when touched, and kept out of runtime imports. They prepare official benchmark inputs/runs for ProgramBench, Terminal-Bench/Harbor, SWE-bench, SWE-bench Pro, GAIA, and OSWorld logs inspection without replacing official scoring harnesses.

You can also override the bind address and port:

ouroboros server --host 127.0.0.1 --port 9000
ouroboros --url http://127.0.0.1:9000 status

Available launch arguments:

Argument	Default	Description
--host	127.0.0.1	Host/interface to bind the web server to
--port	8765	Port to bind the web server to

The same values can also be provided via environment variables:

Variable	Default	Description
OUROBOROS_SERVER_HOST	127.0.0.1	Default bind host
OUROBOROS_SERVER_PORT	8765	Default bind port
OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD	unset	Set to 1 only for trusted Docker/Kubernetes deployments where ingress auth, VPN, a private network, or an auth proxy already protects access

For non-localhost binds, set OUROBOROS_NETWORK_PASSWORD (or use the OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD=1 escape hatch only when ingress/VPN/private-network auth already protects the surface). The full network bind matrix and Docker/Kubernetes deployment policy live in docs/DEPLOYMENT.md — read that before exposing anything beyond loopback.

The Files tab uses your home directory by default only for localhost usage. For Docker or other network-exposed runs, set OUROBOROS_FILE_BROWSER_DEFAULT to an explicit directory. Symlink entries are shown and can be read, edited, copied, moved, uploaded into, and deleted intentionally; root-delete protection still applies to the configured root itself.

Provider Routing

Settings now exposes tabbed provider cards for:

• OpenRouter — default multi-model router
• OpenAI — official OpenAI API (use model values like openai::gpt-5.5)
• OpenAI Compatible — any custom OpenAI-style endpoint (use openai-compatible::...)
• Cloud.ru Foundation Models — Cloud.ru OpenAI-compatible runtime (use cloudru::...)
• GigaChat — Sber GigaChat via the gigachat library, OAuth key or user/password (use gigachat::GigaChat-3-Ultra, etc.)
• Anthropic — direct runtime routing (anthropic::claude-opus-4.8, etc.) plus Claude Agent SDK tools

If OpenRouter is not configured and only official OpenAI is present, untouched default model values are auto-remapped to openai::gpt-5.5 / openai::gpt-5.5-mini so the first-run path does not strand the app on OpenRouter-only defaults.

The Settings page also includes:

• optional /api/model-catalog lookup for configured providers
• centralized Secrets storage for API keys, bridge tokens, passwords, and future skill-requested keys
• a refactored desktop-first tabbed UI with searchable model pickers, segmented effort controls, task-result review mode, masked-secret toggles, explicit Clear actions, and local-model controls

Run Tests

make test

---

Build

Docker (web UI)

Docker is for the web UI/runtime flow, not the desktop bundle. The container binds to 0.0.0.0:8765 by default, and the image now also defaults OUROBOROS_FILE_BROWSER_DEFAULT to ${APP_HOME} so the Files tab always has an explicit network-safe root inside the container.

Browser tools on Linux/Docker: The Dockerfile runs playwright install-deps chromium webkit (authoritative Playwright dependency resolver) and playwright install chromium webkit so browse_page and browser_action work out of the box in the container. For source installs on Linux without Docker, run: python3 -m playwright install-deps chromium webkit (requires sudo / distro package access).

Build the image:

docker build -t ouroboros-web .

Run on the default port:

docker run --rm -p 8765:8765 \
  -e OUROBOROS_NETWORK_PASSWORD='choose-a-password' \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Use a custom port via environment variables:

docker run --rm -p 9000:9000 \
  -e OUROBOROS_SERVER_PORT=9000 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Run with launch arguments instead:

docker run --rm -p 9000:9000 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web --port 9000

Required/important environment variables:

Variable	Required	Description
OUROBOROS_NETWORK_PASSWORD	Optional	Enables the non-loopback password gate when set
OUROBOROS_FILE_BROWSER_DEFAULT	Defaults to ${APP_HOME} in the image	Explicit root directory exposed in the Files tab
OUROBOROS_SERVER_PORT	Optional	Override container listen port
OUROBOROS_SERVER_HOST	Optional	Defaults to 0.0.0.0 in Docker
OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD	Optional	See docs/DEPLOYMENT.md for the trusted-network bind policy

Example: mount a host workspace and expose only that directory in Files:

docker run --rm -p 8765:8765 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Release tag prerequisite

All three platform build scripts (build.sh, build_linux.sh, build_windows.ps1) refuse to package a release unless HEAD is already tagged with v$(cat VERSION) (BIBLE.md Principle 9: "Every release is accompanied by an annotated git tag"). The scripts call scripts/build_repo_bundle.py which embeds the resolved tag into repo_bundle_manifest.json, so the launcher can later verify the packaged bundle matches a real release.

Tag the current commit before running any build script:

git tag -a "v$(tr -d '[:space:]' < VERSION)" -m "Release v$(tr -d '[:space:]' < VERSION)"

If the tag is missing, the build script fails with a clear error instead of producing a bundle tagged with a synthetic/placeholder value. Builds disable Python bytecode writes at build time, then PRECOMPILE the packaged payload (compileall --invalidation-mode unchecked-hash) and SEAL the resulting .pyc inside the macOS signature instead of deleting them — so there is nothing for a normal launch to write into the signed bundle, which would otherwise break the codesign seal. Runtime entrypoints also set PYTHONDONTWRITEBYTECODE with an external cache prefix as defense-in-depth.

macOS (.dmg)

bash scripts/download_python_standalone.sh
OUROBOROS_SIGN=0 bash build.sh

Output: dist/Ouroboros-<VERSION>.dmg, containing Ouroboros.app and Install CLI.command. The app bundle also contains Contents/Resources/bin/ouroboros and install-ouroboros-cli. Chromium browser tooling is bundled in the app. WebKit/iPhone browser checks remain available through the managed Playwright cache and may download WebKit on first engine=webkit use.

build.sh packages the macOS app and DMG. By default it signs with the configured local Developer ID identity; set OUROBOROS_SIGN=0 for an unsigned local release. Unsigned builds require right-click → Open on first launch.

Optional signing & notarization (env vars)

build.sh honours these env overrides so the same script ships local, shared-machine, and CI builds without forking the script:

Env var	Effect
OUROBOROS_SIGN=0	Skip codesigning entirely (unsigned .app + .dmg).
SIGN_IDENTITY="Developer ID Application: <Name> (<TeamID>)"	Override the codesign identity. Useful for forks whose Developer ID is not the upstream default.
APPLE_ID, APPLE_TEAM_ID, APPLE_APP_SPECIFIC_PASSWORD	When all three are set, after codesign the DMG is submitted to Apple via xcrun notarytool submit ... --wait and stapled with xcrun stapler staple so receivers do not need right-click → Open. Missing any one falls back to "signed but not notarized" (no Apple-side ticket exists).

Forks: enabling signed CI builds. The CI release flow (.github/workflows/ci.yml::build) wires the build-script env vars above from GitHub repository secrets, plus a small set of CI-only secrets that import the Developer ID certificate into a temporary keychain on the macOS runner. To exercise the signed-build path in a fork, configure all four of the following as repository secrets (Settings → Secrets and variables → Actions): BUILD_CERTIFICATE_BASE64 (base64-encoded .p12), P12_PASSWORD, KEYCHAIN_PASSWORD (an arbitrary passphrase the workflow uses for its temporary keychain), and APPLE_TEAM_ID. Add APPLE_ID + APPLE_APP_SPECIFIC_PASSWORD to additionally enable notarization. If your Developer ID identity differs from the upstream default, also set SIGN_IDENTITY (e.g. Developer ID Application: <Your Name> (<YOUR_TEAM_ID>)). With no Apple secrets configured the build job falls through to OUROBOROS_SIGN=0 bash build.sh and ships an unsigned DMG identical to v5.0.0 behaviour. See docs/ARCHITECTURE.md §8.1 and docs/DEVELOPMENT.md::"GitHub Actions: secrets in step-level if conditions" for the rationale (job-level env: mapping so step-level if: can read env.*; GHA rejects secrets.* in step if:).

Linux (.tar.gz)

bash scripts/download_python_standalone.sh
bash build_linux.sh

Output: dist/Ouroboros-<VERSION>-linux-<arch>.tar.gz, containing Ouroboros/bin/ouroboros and Ouroboros/bin/install-ouroboros-cli.

Linux native libs: The Chromium and WebKit browser binaries are bundled, but some hosts need native system libraries. If browser tools fail, install deps via the bundled Python (the bare playwright CLI is not on PATH in packaged builds):

./Ouroboros/python-standalone/bin/python3 -m playwright install-deps chromium webkit

Windows (.zip)

powershell -ExecutionPolicy Bypass -File scripts/download_python_standalone.ps1
powershell -ExecutionPolicy Bypass -File build_windows.ps1

Output: dist\Ouroboros-<VERSION>-windows-x64.zip, containing Ouroboros\bin\ouroboros.cmd and Ouroboros\bin\install-ouroboros-cli.cmd.

---

Architecture

Two-process desktop app. The launcher (launcher.py) is an immutable PyWebView shell; it spawns server.py, which runs Starlette + uvicorn plus a supervisor thread that manages worker processes. The agent core lives in ouroboros/, the SPA in web/, the queue/process plane in supervisor/, and the system prompts in prompts/.

For the full file-by-file structural map, the operational layer (every API endpoint, log file, env var, state path), and the rationale layer (the why for every non-trivial design decision), see docs/ARCHITECTURE.md — that is the canonical SSOT (Bible P6) and this README only summarizes it.

Data Layout (~/Ouroboros/)

Created on first launch:

Directory	Contents
repo/	Self-modifying local Git repository
data/state/	Runtime state, budget tracking
data/memory/	Identity, working memory, system profile, knowledge base (including improvement-backlog.md), memory registry
data/logs/	Chat history, events, tool calls
data/uploads/	Chat file attachments (uploaded via paperclip button)

---

Configuration

API Keys

Key	Required	Where to get it
OpenRouter API Key	No	openrouter.ai/keys — default multi-model router
OpenAI API Key	No	platform.openai.com/api-keys — official OpenAI runtime and web search
OpenAI Compatible API Key / Base URL	No	Any OpenAI-style endpoint (proxy, self-hosted gateway, third-party compatible API)
Cloud.ru Foundation Models API Key	No	Cloud.ru Foundation Models provider
GigaChat Authorization Key (or User/Password)	No	developers.sber.ru/studio — Sber GigaChat (GIGACHAT_CREDENTIALS + optional GIGACHAT_SCOPE, or GIGACHAT_USER/GIGACHAT_PASSWORD)
Anthropic API Key	No	console.anthropic.com — direct Anthropic runtime + Claude Agent SDK
Telegram Bot Token	No	@BotFather — used by the optional Telegram bridge skill
GitHub Token	No	github.com/settings/tokens — enables remote sync

All keys are configured through the Settings page in the UI or during the first-run wizard.

Default Models

Slot	Default	Purpose
Main	google/gemini-3.5-flash	Primary reasoning
Heavy	empty → Main	Strong acting/coding lane (OUROBOROS_MODEL_HEAVY; renamed from Code, empty falls back to Main)
Light	empty → Main	Safety checks and fast helper tasks (OUROBOROS_MODEL_LIGHT, empty falls back to Main)
Vision	empty → Main	Caption/VLM lane (OUROBOROS_MODEL_VISION, empty falls back to Main for remote routes; local/blind routes need an explicit reachable vision slot for caption fallback); image input routing is controlled by `OUROBOROS_IMAGE_INPUT_MODE=auto
Consciousness	empty → Main	High-horizon background consciousness
Fallbacks	anthropic/claude-sonnet-4.6	Comma-separated cross-model fallback chain when the primary fails (OUROBOROS_MODEL_FALLBACKS)
Claude Agent SDK	opus[1m]	Anthropic model for Claude Agent SDK advisory/review internals; the [1m] suffix is a Claude Code selector that requests the 1M-context extended mode
Scope Review	openai/gpt-5.5	Scope reviewer slot default; OUROBOROS_SCOPE_REVIEW_MODELS may configure multiple independent slots
Web Search	gpt-5.2	OpenAI Responses API for web search

Task/chat reasoning defaults to medium. Scope review reasoning defaults to high.

Models are configurable in the Settings page. Runtime model slots can target OpenRouter, official OpenAI, OpenAI-compatible endpoints, Cloud.ru, GigaChat, or direct Anthropic. When only official OpenAI is configured and the shipped default model values are still untouched, Ouroboros auto-remaps them to official OpenAI defaults. In OpenAI-only, Anthropic-only, Cloud.ru-only, or GigaChat-only direct-provider mode, review-model lists are normalized automatically: the fallback shape is [main_model, light_model, light_model] (3 commit-triad slots) so both the commit triad and plan_task work out of the box. Explicit duplicate model IDs are valid reviewer slots for stochastic sampling; lower uniqueness means lower reviewer diversity, but the quorum gate counts configured slots rather than unique model IDs. Both the commit triad and plan_task route through the same ouroboros/config.py::get_review_models SSOT. OpenAI-compatible-only setups remain explicit model-selection flows because there is no single universal default model ID for arbitrary compatible endpoints.

File Browser Start Directory

The web UI file browser is rooted at one configurable directory. Users can browse only inside that directory tree.

Variable	Example	Behavior
OUROBOROS_FILE_BROWSER_DEFAULT	/home/app	Sets the root directory of the Files tab

Examples:

OUROBOROS_FILE_BROWSER_DEFAULT=/home/app ouroboros server
OUROBOROS_FILE_BROWSER_DEFAULT=/mnt/shared ouroboros server --port 9000

If the variable is not set, Ouroboros uses the current user's home directory. If the configured path does not exist or is not a directory, Ouroboros also falls back to the home directory.

The Files tab supports:

• downloading any file inside the configured browser root
• uploading a file into the currently opened directory

Uploads do not overwrite existing files. If a file with the same name already exists, the UI will show an error.

---

Commands

Available in the chat interface:

Command	Description
/panic	Emergency stop. Kills ALL processes, closes the application.
/restart	Soft restart. Saves state, kills workers, re-launches.
/status	Shows active workers, task queue, and budget breakdown.
/evolve	Toggle autonomous evolution mode (on/off).
/review	Queue a deep self-review: sends a generated repository atlas plus full core memory artifacts (identity, scratchpad, registry, WORLD, knowledge index, patterns, improvement-backlog) to a 1M-context model for Constitution-grounded analysis. The atlas raw-inlines selected protected/central files (ranked by import-graph centrality), accounts for every tracked path in its manifest, and excludes vendored libraries and operational logs; the in-prompt omitted-files summary is bounded, with full per-file coverage persisted in the atlas manifest. The assembled prompt is sized to an input limit that reserves output headroom inside the 1M window (window minus output reserve and tokenizer margin); if assembly overshoots, the pack retries with a compact atlas manifest and then a deterministic tighter rebuild, and only fails with an explicit error if even the shrunk pack cannot fit.
/bg	Toggle background consciousness loop (start/stop/status).

The same runtime actions are also exposed as compact buttons in the Chat header. All other messages are sent directly to the LLM.

---

Philosophy

The 13 Constitution principles — Agency, Continuity, Meta-over-Patch, Immune Integrity, Self-Creation, LLM-First, Authenticity & Reality Discipline, Minimalism, Becoming, Versioning and Releases, the absorbed Iterations / Spiral lineage, and Epistemic Stability — are defined in full in BIBLE.md. That file is the constitutional SSOT (Bible P4 Ship-of-Theseus protection) and this README intentionally does not paraphrase it.

---

Contributing

External contributions are welcome. See CONTRIBUTING.md for the contributor workflow. The project rules remain in BIBLE.md, docs/ARCHITECTURE.md, docs/DEVELOPMENT.md, and docs/CHECKLISTS.md; the contribution guide only routes to those sources.

---

Version History

Version	Date	Description
6.47.0	2026-06-26	feat: verify-before-done flagship, deep cooperative subagents, workspace-aware code-intel, and the skill-publish desync fix. Reliability: a new core verify_and_record tool runs the agent's declared verification check on the host and writes a durable host-attested receipt (contract kinds: visible_verifier / explicit_command / explicit_metric / artifact_observation / no_visible_machine_contract); a one-shot verify-before-done nudge fires when a turn produced real effects but recorded no grounding, and a BINARY receipt_absent (FR3) / expected_output_ungrounded (M2 zero-grounding, gated on the typed expected_output) objective-axis warning surfaces an unverified-but-clean turn WITHOUT ever downgrading it (anti-oscillation); a deadline-flush prompt salvages a time-boxed deliverable at the tightest milestone. Capability: query_code runs read-only structured code intelligence over an external user_files target (e.g. a benchmark /app) with search_code-shape guards and bounded symlink-safe structural walks; external-workspace HOST process commands scrub the Ouroboros repo from PYTHONPATH so a target's import web/server can't shadow-import the agent (a docker_exec backend already runs in the container's own environment); the artifact-audit nudge is now effect-based; deep COOPERATIVE acting subagents build together in ONE host-minted shared git tree (external_workspace), with a depth-aware reservation so a wide first level can't starve depth. UX: skill→hub publish eligibility is one SSOT predicate the gateway serializes (submit_hub) and the Skills card renders — a no-blocker (clean OR advisory-only warnings) review now enables Submit in the UI, ending the clean-only desync. Bench: the SWE-bench Pro grader prints a RAW Pass@1 headline and keeps all contamination/benchmark-defect analysis in a separate diagnostic CONTAMINATION_AUDIT.md that never adjusts the score (gold is never shown to the solver). New surface: verify_and_record, ouroboros/skill_publish_eligibility.py, submit_hub gateway field.
6.46.0	2026-06-25	feat: GAIA-forensic hardening — generalizable runtime fixes surfaced by a benchmark audit, plus an empirical context-window probe. Runtime: budget exhaustion now TERMINALIZES undispatched queued tasks (fail_tasks, reason_code=budget_exhausted + event/notify) instead of a silent never-dispatched PENDING freeze; search_code gains a wall-clock deadline across the directory walk AND the rg-batch loop (OUROBOROS_SEARCH_CODE_WALL_SEC); web_search gains a backend pin (OUROBOROS_WEBSEARCH_BACKEND, ddgs now a dependency with 429 backoff) so a fixed-model run can force pure retrieval; a config-SSOT OUROBOROS_OR_PROVIDER (resilience/repro presets) routes OpenRouter providers for rate-limit resilience without losing prompt-cache warmth, generalized behind a supports_message_cache_control predicate. Answer integrity: a tool-count-stamped latch recovers a produced FINAL ANSWER whose marker a later round DROPS (a deliberate post-review marker — a genuine correction — stays authoritative, and new tool work invalidates a now-stale latch), and acceptance review on the advisory task surface stops over-failing a grounded answer (majority-not-single-FAIL, no solved→DEGRADED on empty coach) so review can ground but never single-vote-DOWNGRADE a correct answer — the P3 commit/scope immune gate is untouched. Security: user_files honors OUROBOROS_USER_FILES_ROOT (jailed scratch home), and the authoritative observability blob is redacted by default (OUROBOROS_OBSERVABILITY_KEEP_RAW opt-in) with a broadened secret matcher. Capability: a generative context-window probe empirically confirms a route's ≥1M window from a FREE over-window reject (only on the explicit Max toggle/save, never from a possibly-paid 200), plus a cloud.ru route base_url fix. Bench: the GAIA adapter stages attachments robustly, injects the FINAL ANSWER: protocol, crash-isolates per-sample timeouts, and exposes per-config knobs.
6.45.5	2026-06-24	fix: CI expectation compatibility for credential-aware tool gating. Clear inherited timeout env in shell timeout tests, seed web-search availability where resource-gate behavior is under test, and accept central CAPABILITY_UNAVAILABLE for Claude Code auth-gate expectations.
6.45.4	2026-06-24	fix: Terminal-Bench timeout smoke expectation after safety-buffer accounting. Align the hostile-workspace runner test with the adapter’s effective task-timeout buffer (900 -> 870) while preserving the generated task timeout contract.
6.45.3	2026-06-24	fix: structural registry tests after credential-aware tool discovery. Keep missing-credential capability hiding for real task contexts while allowing bare registry/static policy tests to inspect the full structural tool inventory; move strict public-arg validation after runtime-mode/heal/resource gates so safety blocks keep precedence.
6.45.2	2026-06-24	fix: CI smoke compatibility after v6.45.1. Align tests with send-time image routing and model-slot copy, record reviewed complexity debt from the merged evolution fix, and keep ruff/quick-test gates green without force-pushing the already-published branch.
6.45.1	2026-06-24	fix: release-path lint and GAIA scoring hardening. Fix-forward after CI: remove two deterministic ruff F841 lint issues, keep GAIA disabled-tool parsing under argparse.REMAINDER, parse official Inspect JSON/eval scores before local result diagnostics, preserve GAIA file attachments safely, and keep benchmark settings secret-isolated while documenting the light-mode safety correction.
6.45.0	2026-06-24	feat: first-class vision routing and maintained GAIA adapter. Vision: a new OUROBOROS_MODEL_VISION slot and OUROBOROS_IMAGE_INPUT_MODE (auto/caption/inline/off) route image blocks at send time without mutating the canonical transcript: vision-capable models keep inline pixels, blind models can receive generic captions, and placeholders remain fail-closed. vlm_query and analyze_screenshot are now vision tools rather than _WEB_TOOLS; benchmark adapters can withhold them by name through disabled_tools when isolation requires it. Devtools: devtools/benchmarks/gaia/ adds a reviewed GAIA adapter using the official inspect_evals/gaia scorer, structured --result-json-out answer extraction, fixed-model settings with required acceptance review, and diagnostic-only lenient normalization.
6.44.0	2026-06-24	feat: benchmark-scoped acceptance review, capability availability, CLI tool denylist, and Pro patch hygiene. SWE-bench Pro now enables OUROBOROS_TASK_REVIEW_MODE=required only inside its adapter settings while the global default stays auto; the task-acceptance reviewer prompt derives criteria from the full issue narrative, enumerates affected surfaces, and requires per-criterion grader-mirroring evidence. Tool discovery now hides built-ins whose credentials/backends are unavailable (claude_code_edit, web_search, GitHub tools) with missing_credential capability omissions and execution-time CAPABILITY_UNAVAILABLE; ouroboros run --disable-tools threads the existing task_contract.disabled_tools policy into CLI-created tasks, and Pro disables web/browser/VLM/Claude-Code tools by name. Registry argument errors now show public tool parameters and explicit aliases (max_entries -> max_results, redundant root ignored on VCS tools) without leaking private handler names. Pro patch capture is shared through capture_patch.sh, drops incidental lockfiles whose sibling manifests did not change while preserving pure lockfile fixes, and defaults to fixed-model baseline measurement (--evolution opts into carried post-task evolution).
6.43.0	2026-06-24	fix: managed-update cache truth, verified official-hub attestation, skill-deps diagnostics, and plan-review tooling. Updates: passive managed-update status now ignores stale cached availability once HEAD already matches the cached target, eliminating the phantom Update X -> X pill and its 409 dead-end without adding a hot-path fetch. Skills: owner-attestation remains owner-only and deterministic-preflight-gated, but now also covers freshly hash-verified official OuroborosHub payloads (native, ClawHub, and unverified hub payloads stay non-attestable); the safety/checklist/docs contract and UI affordance mirror that trust boundary. Isolated skill dependency installs now preserve a bounded stderr tail in deps.json.error, so failed --only-binary pip installs report the actual wheel/platform problem instead of generic pip install failed. Tooling: scripts/run_plan_review.py provides the same configured multi-model plan-review panel as plan_task without the live scout swarm for pre-code operator gates.
Older releases are preserved in Git tags and GitHub releases. Older 6.x rows, the 5.2.0 through 5.33.0-rc.6 rows, and former 4.0.0 rows are rolled off to respect the P9 changelog cap; their full bodies remain at their git tags.

---

License

MIT License

Created by Anton Razzhigaev & Andrew Kaznacheev