Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
62 commits
Select commit Hold shift + click to select a range
53ead36
Revise README with links and enhanced project details
ananay Jun 4, 2026
22f65d4
Update README.md
ananay Jun 4, 2026
5889b8f
Update README.md
ananay Jun 4, 2026
ff00dd5
Update README.md
ananay Jun 4, 2026
57086e2
Change to MIT License
ananay Jun 10, 2026
da6ad17
Revise README with new project name and license
ananay Jun 10, 2026
16907fe
Release 0.1.1: custom endpoint support, prompt_caching setting, setup…
ananay Jun 11, 2026
dda73e5
Release 0.1.2: ignore unknown keys in CWD .env to prevent startup crash
ananay Jun 11, 2026
67d79b9
Create CODE_OF_CONDUCT.md
ananay Jun 11, 2026
b2032a4
Document uv install in README
ananay Jun 12, 2026
eaa2338
Redesign TUI: OpenHack brand identity, ground-mark logo, landing lockup
ananay Jul 1, 2026
68783a4
Interactive hacking agent: tool layer + non-TUI mode (Milestone 1)
ananay Jul 1, 2026
f7ccc63
Add plan mode: read-only PlanAgent + `openhack plan`
ananay Jul 1, 2026
0bc21d8
Harden plan mode: never blank output; gather-once-then-write prompt
ananay Jul 1, 2026
0ff64e8
Dedupe final answer in non-TUI runner
ananay Jul 1, 2026
e59c661
Add recon + OOB agent tools (active exploitation groundwork)
ananay Jul 1, 2026
481d099
Add headless-browser DAST tool + async tool dispatch in registry
ananay Jul 1, 2026
86a887f
Provider flexibility: connect any provider/model (bring-your-own-key)
ananay Jul 1, 2026
61ea386
Wire interactive agent into the TUI (flagship)
ananay Jul 1, 2026
4668be6
Fix: TUI follow-up messages continue the agent conversation
ananay Jul 2, 2026
64b010b
Show user messages in the transcript
ananay Jul 2, 2026
e0a2240
Chat-style transcript: speaker bar only, no agent label
ananay Jul 2, 2026
5ad2736
Cleaner chat: drop agents sidebar + space out messages
ananay Jul 2, 2026
f2fc13d
Move shortcuts off the tab bar to a bottom keybar
ananay Jul 2, 2026
12ea3f3
Hide scan sidebar in agent chats; space out the input box
ananay Jul 2, 2026
37302bd
Chat-first transcript: no tabs, clean tool lines, up/down scrolls
ananay Jul 2, 2026
8e9f385
Command cleanup + findings tools for the agent
ananay Jul 2, 2026
a81a7d3
Make /model discoverable: list the served models
ananay Jul 3, 2026
9ffddc4
Default to glm-5.2 across the CLI
ananay Jul 3, 2026
7188095
Persist agent sessions (with tokens/cost/trace) for debugging
ananay Jul 3, 2026
df40437
Support all 4 served models (glm-5.2, kimi-k2.5, gemma-4-31b, mistral)
ananay Jul 3, 2026
64d4e77
Stream the agent's answer into the transcript as it arrives
ananay Jul 3, 2026
e714fa5
Fix scroll crash + show exact tool command/args and results
ananay Jul 3, 2026
549adbb
Redo the processing indicator: clean spinner + live status
ananay Jul 7, 2026
16f7e0e
Add @path file/directory references in the input (OpenCode-style)
ananay Jul 7, 2026
3de049f
@ references: support ../, ./, /, ~ (browse outside cwd)
ananay Jul 7, 2026
144cef2
/model opens a scrollable picker instead of a status-line string
ananay Jul 7, 2026
ee331cb
Add 110-task pentest catalog for trying OpenHack
ananay Jul 7, 2026
10301dc
Add first real-world eval results
ananay Jul 7, 2026
3f87022
Scope discipline: do exactly the ask + 100 advanced tasks
ananay Jul 7, 2026
cfca8cf
Add XBOW live-exploitation eval results
ananay Jul 7, 2026
f8a9a1a
Add sqlmap_test tool + teach the agent to use specialists
ananay Jul 8, 2026
5353310
Make sqlmap mandatory for SQLi in the agent prompt (hard rule)
ananay Jul 8, 2026
9f6c1ab
Tighten shell output cap + record honest sqlmap findings
ananay Jul 8, 2026
7327972
Persist full structured trace from headless hack runs
ananay Jul 9, 2026
5f7ac05
Full XBOW benchmark results: 54/104 (52% raw, 61% of runnable)
ananay Jul 9, 2026
623c090
XBOW model comparison: DeepSeek V4 Pro 1/104 vs glm-5.2 54/104
ananay Jul 9, 2026
4dba4c7
Anti-thrash: durable ledger + anti-repetition + progress-aware stop
ananay Jul 9, 2026
16d0f1e
Fix anti-thrash regression: result-novelty stop + restore 60-turn cap
ananay Jul 9, 2026
02088b6
XBOW v2 results + leaderboard: 86/104 best-of-3 (72 single-run) on AW…
ananay Jul 10, 2026
8778dbb
XBOW white-box run: 84/104 (81% raw, 88% runnable) on glm-5.2
ananay Jul 10, 2026
6bbc902
Grok 4.5 model experiment: 10/13 of glm-5.2's hardest black-box fails
ananay Jul 10, 2026
dfeb028
Add grok-4.5 pricing ($2/$6) + full-104 Grok harness
ananay Jul 10, 2026
24f0f94
Make Grok 4.5 the default OpenHack model + add to /model picker
ananay Jul 10, 2026
41c0fd5
Grok 4.5 full 104 measured: 88/104 (85% raw, 93% runnable), ~same cos…
ananay Jul 10, 2026
e10717d
Add coverage matrix (glm/Grok x black/white-box) to leaderboard
ananay Jul 11, 2026
f78ecbe
Specialists Phase 0: foundation (SpecialistAgent + factory + stateful…
ananay Jul 11, 2026
a5a4d32
Specialists Phase 1+2: dispatch_specialist wiring (black-box path)
ananay Jul 11, 2026
efd6c9e
Document specialist-layer validation: model is the lever, not archite…
ananay Jul 12, 2026
ba031bd
Preserve Grok 4.5 per-benchmark transcripts (evidence trail, box-only)
ananay Jul 12, 2026
c487016
TUI: solid black background (drop the green-tinted canvas), keep gree…
ananay Jul 15, 2026
735f0aa
Bump pydantic-settings from 2.13.1 to 2.14.2
dependabot[bot] Jul 20, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
128 changes: 128 additions & 0 deletions CODE_OF_CONDUCT.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,128 @@
# Contributor Covenant Code of Conduct

## Our Pledge

We as members, contributors, and leaders pledge to make participation in our
community a harassment-free experience for everyone, regardless of age, body
size, visible or invisible disability, ethnicity, sex characteristics, gender
identity and expression, level of experience, education, socio-economic status,
nationality, personal appearance, race, religion, or sexual identity
and orientation.

We pledge to act and interact in ways that contribute to an open, welcoming,
diverse, inclusive, and healthy community.

## Our Standards

Examples of behavior that contributes to a positive environment for our
community include:

* Demonstrating empathy and kindness toward other people
* Being respectful of differing opinions, viewpoints, and experiences
* Giving and gracefully accepting constructive feedback
* Accepting responsibility and apologizing to those affected by our mistakes,
and learning from the experience
* Focusing on what is best not just for us as individuals, but for the
overall community

Examples of unacceptable behavior include:

* The use of sexualized language or imagery, and sexual attention or
advances of any kind
* Trolling, insulting or derogatory comments, and personal or political attacks
* Public or private harassment
* Publishing others' private information, such as a physical or email
address, without their explicit permission
* Other conduct which could reasonably be considered inappropriate in a
professional setting

## Enforcement Responsibilities

Community leaders are responsible for clarifying and enforcing our standards of
acceptable behavior and will take appropriate and fair corrective action in
response to any behavior that they deem inappropriate, threatening, offensive,
or harmful.

Community leaders have the right and responsibility to remove, edit, or reject
comments, commits, code, wiki edits, issues, and other contributions that are
not aligned to this Code of Conduct, and will communicate reasons for moderation
decisions when appropriate.

## Scope

This Code of Conduct applies within all community spaces, and also applies when
an individual is officially representing the community in public spaces.
Examples of representing our community include using an official e-mail address,
posting via an official social media account, or acting as an appointed
representative at an online or offline event.

## Enforcement

Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported to the community leaders responsible for enforcement at
.
All complaints will be reviewed and investigated promptly and fairly.

All community leaders are obligated to respect the privacy and security of the
reporter of any incident.

## Enforcement Guidelines

Community leaders will follow these Community Impact Guidelines in determining
the consequences for any action they deem in violation of this Code of Conduct:

### 1. Correction

**Community Impact**: Use of inappropriate language or other behavior deemed
unprofessional or unwelcome in the community.

**Consequence**: A private, written warning from community leaders, providing
clarity around the nature of the violation and an explanation of why the
behavior was inappropriate. A public apology may be requested.

### 2. Warning

**Community Impact**: A violation through a single incident or series
of actions.

**Consequence**: A warning with consequences for continued behavior. No
interaction with the people involved, including unsolicited interaction with
those enforcing the Code of Conduct, for a specified period of time. This
includes avoiding interactions in community spaces as well as external channels
like social media. Violating these terms may lead to a temporary or
permanent ban.

### 3. Temporary Ban

**Community Impact**: A serious violation of community standards, including
sustained inappropriate behavior.

**Consequence**: A temporary ban from any sort of interaction or public
communication with the community for a specified period of time. No public or
private interaction with the people involved, including unsolicited interaction
with those enforcing the Code of Conduct, is allowed during this period.
Violating these terms may lead to a permanent ban.

### 4. Permanent Ban

**Community Impact**: Demonstrating a pattern of violation of community
standards, including sustained inappropriate behavior, harassment of an
individual, or aggression toward or disparagement of classes of individuals.

**Consequence**: A permanent ban from any sort of public interaction within
the community.

## Attribution

This Code of Conduct is adapted from the [Contributor Covenant][homepage],
version 2.0, available at
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.

Community Impact Guidelines were inspired by [Mozilla's code of conduct
enforcement ladder](https://github.com/mozilla/diversity).

[homepage]: https://www.contributor-covenant.org

For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at
https://www.contributor-covenant.org/translations.
Loading
Loading